huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'huggingface:main' into main

Browse Source
This commit is contained in:
Marcus Dunn 2023-08-15 14:52:04 -07:00 committed by GitHub
commit f65d703de4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
18 changed files with 365 additions and 323 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/build_documentation.yml vendored
View File

@ -2,6 +2,8 @@ name: Build documentation
on:
push:
paths:
- "docs/source/**"
branches:
- main
- doc-builder*

2
.github/workflows/build_pr_documentation.yml vendored
View File

@ -2,6 +2,8 @@ name: Build PR Documentation
on:
pull_request:
paths:
- "docs/source/**"
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}

381
Cargo.lock generated
View File

@ -50,9 +50,9 @@ dependencies = [
[[package]]
name = "aho-corasick"
version = "1.0.2"
version = "1.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "43f6cb1bf222025340178f382c426f13757b2960e89779dfcb319c32542a5a41"
checksum = "86b8f9420f797f2d9e935edf629310eb938a0d839f984e25327f3c7eed22300c"
dependencies = [
"memchr",
]
@ -98,9 +98,9 @@ dependencies = [
[[package]]
name = "anstyle-wincon"
version = "1.0.1"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "180abfa45703aebe0093f79badacc01b8fd4ea2e35118747e5811127f926e188"
checksum = "c677ab05e09154296dd37acecd46420c17b9713e8366facafa8fc0885167cf4c"
dependencies = [
"anstyle",
"windows-sys 0.48.0",
@ -108,9 +108,9 @@ dependencies = [
[[package]]
name = "anyhow"
version = "1.0.71"
version = "1.0.72"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c7d0618f0e0b7e8ff11427422b64564d5fb0be1940354bfe2e0529b18a9d9b8"
checksum = "3b13c32d80ecc7ab747b80c3784bce54ee8a7a0cc4fbda9bf4cda2cf6fe90854"
[[package]]
name = "arc-swap"
@ -148,18 +148,18 @@ checksum = "16e62a023e7c117e27523144c5d2459f4397fcc3cab0085af8e2224f643a0193"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
]
[[package]]
name = "async-trait"
version = "0.1.71"
version = "0.1.73"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a564d521dd56509c4c47480d00b80ee55f7e385ae48db5744c67ad50c92d2ebf"
checksum = "bc00ceb34980c03614e35a3a4e218276a0a824e911d07651cd0d858a51e8c0f0"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
]
[[package]]
@ -193,9 +193,9 @@ dependencies = [
[[package]]
name = "axum"
version = "0.6.18"
version = "0.6.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f8175979259124331c1d7bf6586ee7e0da434155e4b2d48ec2c8386281d8df39"
checksum = "3b829e4e32b91e643de6eafe82b1d90675f5874230191a4ffbc1b336dec4d6bf"
dependencies = [
"async-trait",
"axum-core",
@ -297,9 +297,9 @@ checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
[[package]]
name = "bitflags"
version = "2.3.3"
version = "2.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "630be753d4e58660abd17930c71b647fe46c27ea6b63cc59e1e3851406972e42"
checksum = "b4682ae6287fcf752ecaabbfcc7b6f9b72aa33933dc23a554d853aea8eea8635"
[[package]]
name = "block-buffer"
@ -385,11 +385,12 @@ checksum = "df8670b8c7b9dae1793364eafadf7239c40d669904660c5960d74cfd80b46a53"
[[package]]
name = "cc"
version = "1.0.79"
version = "1.0.82"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "50d30906286121d95be3d479533b458f87493b30a4b5f79a607db8f5d11aa91f"
checksum = "305fe645edc1442a0fa8b6726ba61d422798d37a52e12eaecf4b022ebbb88f01"
dependencies = [
"jobserver",
"libc",
]
[[package]]
@ -410,9 +411,9 @@ dependencies = [
[[package]]
name = "clap"
version = "4.3.11"
version = "4.3.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1640e5cc7fb47dbb8338fd471b105e7ed6c3cb2aeb00c2e067127ffd3764a05d"
checksum = "c27cdf28c0f604ba3f512b0c9a409f8de8513e4816705deb0498b627e7c3a3fd"
dependencies = [
"clap_builder",
"clap_derive",
@ -421,9 +422,9 @@ dependencies = [
[[package]]
name = "clap_builder"
version = "4.3.11"
version = "4.3.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "98c59138d527eeaf9b53f35a77fcc1fad9d883116070c63d5de1c7dc7b00c72b"
checksum = "08a9f1ab5e9f01a9b81f202e8562eb9a10de70abf9eaeac1be465c28b75aa4aa"
dependencies = [
"anstream",
"anstyle",
@ -433,14 +434,14 @@ dependencies = [
[[package]]
name = "clap_derive"
version = "4.3.2"
version = "4.3.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b8cd2b2a819ad6eec39e8f1d6b53001af1e5469f8c177579cdaeb313115b825f"
checksum = "54a9bb5758fc5dfe728d1019941681eccaf0cf8a4189b692a0ee2f2ecf90a050"
dependencies = [
"heck",
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
]
[[package]]
@ -644,6 +645,12 @@ dependencies = [
"parking_lot_core",
]
[[package]]
name = "deranged"
version = "0.3.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7684a49fb1af197853ef7b2ee694bc1f5b4179556f1e5710e1760c5db6f5e929"
[[package]]
name = "derive_builder"
version = "0.12.0"
@ -717,9 +724,9 @@ dependencies = [
[[package]]
name = "either"
version = "1.8.1"
version = "1.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7fcaabb2fef8c910e7f4c7ce9f67a1283a1715879a7c230ca9d6d1ae31f16d91"
checksum = "a26ae43d7bcc3b814de94796a5e736d4029efb0ee900c12e2d54c993ad1a1e07"
[[package]]
name = "encode_unicode"
@ -744,9 +751,9 @@ checksum = "5443807d6dff69373d433ab9ef5378ad8df50ca6298caf15de6e52e24aaf54d5"
[[package]]
name = "errno"
version = "0.3.1"
version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4bcfec3a70f97c962c307b2d2c56e358cf1d00b558d74262b5f929ee8cc7e73a"
checksum = "6b30f669a7961ef1631673d2766cc92f52d64f7ef354d4fe0ddfd30ed52f0f4f"
dependencies = [
"errno-dragonfly",
"libc",
@ -774,22 +781,19 @@ dependencies = [
[[package]]
name = "fastrand"
version = "1.9.0"
version = "2.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e51093e27b0797c359783294ca4f0a911c270184cb10f85783b118614a1501be"
dependencies = [
"instant",
]
checksum = "6999dc1837253364c2ebb0704ba97994bd874e8f195d665c50b7548f6ea92764"
[[package]]
name = "filetime"
version = "0.2.21"
version = "0.2.22"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5cbc844cecaee9d4443931972e1289c8ff485cb4cc2767cb03ca139ed6885153"
checksum = "d4029edd3e734da6fe05b6cd7bd2960760a616bd2ddd0d59a0124746d6272af0"
dependencies = [
"cfg-if",
"libc",
"redox_syscall 0.2.16",
"redox_syscall 0.3.5",
"windows-sys 0.48.0",
]
@ -930,7 +934,7 @@ checksum = "89ca545a94061b6365f2c7355b4b32bd20df3ff95f02da9329b34ccc3bd6ee72"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
]
[[package]]
@ -1113,9 +1117,9 @@ dependencies = [
[[package]]
name = "http-range-header"
version = "0.3.0"
version = "0.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0bfe8eed0a9285ef776bb792479ea3834e8b94e13d615c2f66d03dd50a435a29"
checksum = "add0ab9360ddbd88cfeb3bd9574a1d85cfdfa14db10b3e21d3700dbc4328758f"
[[package]]
name = "httparse"
@ -1125,9 +1129,9 @@ checksum = "d897f394bad6a705d5f4104762e116a75639e470d80901eed05a860a95cb1904"
[[package]]
name = "httpdate"
version = "1.0.2"
version = "1.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c4a1e36c821dbe04574f602848a19f742f4fb3c98d40449f11bcad18d6b17421"
checksum = "df3b46402a9d5adb4c86a0cf463f42e19994e3ee891101b1841f30a545cb49a9"
[[package]]
name = "hyper"
@ -1146,7 +1150,7 @@ dependencies = [
"httpdate",
"itoa",
"pin-project-lite",
"socket2",
"socket2 0.4.9",
"tokio",
"tower-service",
"tracing",
@ -1248,26 +1252,6 @@ dependencies = [
"generic-array",
]
[[package]]
name = "instant"
version = "0.1.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7a5bbe824c507c5da5956355e86a746d82e0e1464f65d862cc5e71da70e94b2c"
dependencies = [
"cfg-if",
]
[[package]]
name = "io-lifetimes"
version = "1.0.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "eae7b9aee968036d54dce06cebaefd919e4472e753296daccd6d344e3e2df0c2"
dependencies = [
"hermit-abi",
"libc",
"windows-sys 0.48.0",
]
[[package]]
name = "ipnet"
version = "2.8.0"
@ -1281,7 +1265,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cb0889898416213fab133e1d33a0e5858a48177452750691bde3666d0fdbaf8b"
dependencies = [
"hermit-abi",
"rustix 0.38.4",
"rustix",
"windows-sys 0.48.0",
]
@ -1314,9 +1298,9 @@ dependencies = [
[[package]]
name = "itoa"
version = "1.0.8"
version = "1.0.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "62b02a5381cc465bd3041d84623d0fa3b66738b52b8e2fc3bab8ad63ab032f4a"
checksum = "af150ab688ff2122fcef229be89cb50dd66af9e01a4ff320cc137eecc9bacc38"
[[package]]
name = "jobserver"
@ -1356,15 +1340,9 @@ checksum = "f7012b1bbb0719e1097c47611d3898568c546d597c2e74d66f6087edd5233ff4"
[[package]]
name = "linux-raw-sys"
version = "0.3.8"
version = "0.4.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ef53942eb7bf7ff43a617b3e2c1c4a5ecf5944a7c1bc12d7ee39bbb15e5c1519"
[[package]]
name = "linux-raw-sys"
version = "0.4.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "09fc20d2ca12cb9f044c93e3bd6d32d523e6e2ec3db4f7b2939cd99026ecd3f0"
checksum = "57bcfdad1b858c2db7c38303a6d2ad4dfaf5eb53dfeb0910128b2c26d6158503"
[[package]]
name = "lock_api"
@ -1378,9 +1356,9 @@ dependencies = [
[[package]]
name = "log"
version = "0.4.19"
version = "0.4.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b06a4cde4c0f271a446782e3eff8de789548ce57dbc8eca9292c27f4a42004b4"
checksum = "b5e6163cb8c49088c2c36f57875e58ccd8c87c7427f7fbd50ea6710b2f3f2e8f"
[[package]]
name = "mach2"
@ -1424,9 +1402,9 @@ dependencies = [
[[package]]
name = "matchit"
version = "0.7.0"
version = "0.7.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b87248edafb776e59e6ee64a79086f65890d3510f2c656c000bf2a7e8a0aea40"
checksum = "ed1202b2a6f884ae56f04cff409ab315c5ce26b5e58d7412e484f01fd52f52ef"
[[package]]
name = "memchr"
@ -1489,7 +1467,7 @@ checksum = "ddece26afd34c31585c74a4db0630c376df271c285d682d1e55012197830b6df"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
]
[[package]]
@ -1552,9 +1530,9 @@ dependencies = [
[[package]]
name = "monostate"
version = "0.1.8"
version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3f3f57a8802842f648026a33c3d2e3bb41bb309a35b1609bd7ef2b060b8b6b1b"
checksum = "15f370ae88093ec6b11a710dec51321a61d420fafd1bad6e30d01bd9c920e8ee"
dependencies = [
"monostate-impl",
"serde",
@ -1562,13 +1540,13 @@ dependencies = [
[[package]]
name = "monostate-impl"
version = "0.1.8"
version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e72f4d2e10fde62a0f2fcb4b44ccbf4f9899dcc30c9193449f8dfb9123d71377"
checksum = "371717c0a5543d6a800cac822eac735aa7d2d2fbb41002e9856a4089532dbdce"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
]
[[package]]
@ -1705,9 +1683,9 @@ dependencies = [
[[package]]
name = "num-traits"
version = "0.2.15"
version = "0.2.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "578ede34cf02f8924ab9447f50c28075b4d3e5b269972345e7e0372b38c6cdcd"
checksum = "f30b0abd723be7e2ffca1272140fac1a2f084c77ec3e123c192b66af1ee9e6c2"
dependencies = [
"autocfg",
"libm",
@ -1783,9 +1761,9 @@ dependencies = [
[[package]]
name = "openssl"
version = "0.10.55"
version = "0.10.56"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "345df152bc43501c5eb9e4654ff05f794effb78d4efe3d53abc158baddc0703d"
checksum = "729b745ad4a5575dd06a3e1af1414bd330ee561c01b3899eb584baeaa8def17e"
dependencies = [
"bitflags 1.3.2",
"cfg-if",
@ -1804,7 +1782,7 @@ checksum = "a948666b637a0f465e8564c73e89d4dde00d72d4d473cc972f390fc3dcee7d9c"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
]
[[package]]
@ -1815,9 +1793,9 @@ checksum = "ff011a302c396a5197692431fc1948019154afc178baf7d8e37367442a4601cf"
[[package]]
name = "openssl-sys"
version = "0.9.90"
version = "0.9.91"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "374533b0e45f3a7ced10fcaeccca020e66656bc03dac384f852e4e5a7a8104a6"
checksum = "866b5f16f90776b9bb8dc1e1802ac6f0513de3a7a7465867bfbc563dc737faac"
dependencies = [
"cc",
"libc",
@ -2005,9 +1983,9 @@ dependencies = [
[[package]]
name = "paste"
version = "1.0.13"
version = "1.0.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b4b27ab7be369122c218afc2079489cdcb4b517c0a3fc386ff11e1fedfcc2b35"
checksum = "de3145af08024dea9fa9914f381a17b8fc6034dfb00f3a84013f7ff43f29ed4c"
[[package]]
name = "pbkdf2"
@ -2039,29 +2017,29 @@ dependencies = [
[[package]]
name = "pin-project"
version = "1.1.2"
version = "1.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "030ad2bc4db10a8944cb0d837f158bdfec4d4a4873ab701a95046770d11f8842"
checksum = "fda4ed1c6c173e3fc7a83629421152e01d7b1f9b7f65fb301e490e8cfc656422"
dependencies = [
"pin-project-internal",
]
[[package]]
name = "pin-project-internal"
version = "1.1.2"
version = "1.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ec2e072ecce94ec471b13398d5402c188e76ac03cf74dd1a975161b23a3f6d9c"
checksum = "4359fd9c9171ec6e8c62926d6faaf553a8dc3f64e1507e76da7911b4f6a04405"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
]
[[package]]
name = "pin-project-lite"
version = "0.2.10"
version = "0.2.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4c40d25201921e5ff0c862a505c6557ea88568a4e3ace775ab55e93f2f4f9d57"
checksum = "12cc1b0bf1727a77a54b6654e7b5f1af8604923edc8b81885f8ec92f9e3f0a05"
[[package]]
name = "pin-utils"
@ -2077,9 +2055,9 @@ checksum = "26072860ba924cbfa98ea39c8c19b4dd6a4a25423dbdf219c1eca91aa0cf6964"
[[package]]
name = "portable-atomic"
version = "1.4.0"
version = "1.4.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d220334a184db82b31b83f5ff093e3315280fb2b6bbc032022b2304a509aab7a"
checksum = "f32154ba0af3a075eefa1eda8bb414ee928f62303a54ea85b8d6638ff1a6ee9e"
[[package]]
name = "ppv-lite86"
@ -2123,9 +2101,9 @@ dependencies = [
[[package]]
name = "proc-macro2"
version = "1.0.64"
version = "1.0.66"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "78803b62cbf1f46fde80d7c0e803111524b9877184cfe7c3033659490ac7a7da"
checksum = "18fb31db3f9bddb2ea821cde30a9f70117e3f119938b5ee630b7403aa6e2ead9"
dependencies = [
"unicode-ident",
]
@ -2202,9 +2180,9 @@ dependencies = [
[[package]]
name = "quote"
version = "1.0.29"
version = "1.0.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "573015e8ab27661678357f27dc26460738fd2b6c86e46f386fde94cb5d913105"
checksum = "50f3b39ccfb720540debaa0164757101c08ecb8d326b15358ce76a62c7e85965"
dependencies = [
"proc-macro2",
]
@ -2325,13 +2303,13 @@ dependencies = [
[[package]]
name = "regex"
version = "1.9.1"
version = "1.9.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b2eae68fc220f7cf2532e4494aded17545fce192d59cd996e0fe7887f4ceb575"
checksum = "81bc1d4caf89fac26a70747fe603c130093b53c773888797a6329091246d651a"
dependencies = [
"aho-corasick 1.0.2",
"aho-corasick 1.0.3",
"memchr",
"regex-automata 0.3.3",
"regex-automata 0.3.6",
"regex-syntax 0.7.4",
]
@ -2346,11 +2324,11 @@ dependencies = [
[[package]]
name = "regex-automata"
version = "0.3.3"
version = "0.3.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "39354c10dd07468c2e73926b23bb9c2caca74c5501e38a35da70406f1d923310"
checksum = "fed1ceff11a1dddaee50c9dc8e4938bd106e9d89ae372f192311e7da498e3b69"
dependencies = [
"aho-corasick 1.0.2",
"aho-corasick 1.0.3",
"memchr",
"regex-syntax 0.7.4",
]
@ -2440,7 +2418,7 @@ dependencies = [
"quote",
"rust-embed-utils",
"shellexpand",
"syn 2.0.25",
"syn 2.0.28",
"walkdir",
]
@ -2471,28 +2449,14 @@ dependencies = [
[[package]]
name = "rustix"
version = "0.37.23"
version = "0.38.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4d69718bf81c6127a49dc64e44a742e8bb9213c0ff8869a22c308f84c1d4ab06"
checksum = "19ed4fa021d81c8392ce04db050a3da9a60299050b7ae1cf482d862b54a7218f"
dependencies = [
"bitflags 1.3.2",
"errno",
"io-lifetimes",
"libc",
"linux-raw-sys 0.3.8",
"windows-sys 0.48.0",
]
[[package]]
name = "rustix"
version = "0.38.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0a962918ea88d644592894bc6dc55acc6c0956488adcebbfb6e273506b7fd6e5"
dependencies = [
"bitflags 2.3.3",
"bitflags 2.4.0",
"errno",
"libc",
"linux-raw-sys 0.4.3",
"linux-raw-sys",
"windows-sys 0.48.0",
]
@ -2519,15 +2483,15 @@ dependencies = [
[[package]]
name = "rustversion"
version = "1.0.13"
version = "1.0.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dc31bd9b61a32c31f9650d18add92aa83a49ba979c143eefd27fe7177b05bd5f"
checksum = "7ffc183a10b4478d04cbbbfc96d0873219d962dd5accaff2ffbd4ceb7df837f4"
[[package]]
name = "ryu"
version = "1.0.14"
version = "1.0.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fe232bdf6be8c8de797b22184ee71118d63780ea42ac85b61d1baa6d3b782ae9"
checksum = "1ad4cc8da4ef723ed60bced201181d83791ad433213d8c24efffda1eec85d741"
[[package]]
name = "same-file"
@ -2549,9 +2513,9 @@ dependencies = [
[[package]]
name = "scopeguard"
version = "1.1.0"
version = "1.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd"
checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
[[package]]
name = "sct"
@ -2565,9 +2529,9 @@ dependencies = [
[[package]]
name = "security-framework"
version = "2.9.1"
version = "2.9.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1fc758eb7bffce5b308734e9b0c1468893cae9ff70ebf13e7090be8dcbcc83a8"
checksum = "05b64fb303737d99b81884b2c63433e9ae28abebe5eb5045dcdd175dc2ecf4de"
dependencies = [
"bitflags 1.3.2",
"core-foundation",
@ -2578,9 +2542,9 @@ dependencies = [
[[package]]
name = "security-framework-sys"
version = "2.9.0"
version = "2.9.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f51d0c0d83bec45f16480d0ce0058397a69e48fcdc52d1dc8855fb68acbd31a7"
checksum = "e932934257d3b408ed8f30db49d85ea163bfe74961f017f405b025af298f0c7a"
dependencies = [
"core-foundation-sys",
"libc",
@ -2588,35 +2552,35 @@ dependencies = [
[[package]]
name = "semver"
version = "1.0.17"
version = "1.0.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bebd363326d05ec3e2f532ab7660680f3b02130d780c299bca73469d521bc0ed"
checksum = "b0293b4b29daaf487284529cc2f5675b8e57c61f70167ba415a463651fd6a918"
[[package]]
name = "serde"
version = "1.0.171"
version = "1.0.183"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "30e27d1e4fd7659406c492fd6cfaf2066ba8773de45ca75e855590f856dc34a9"
checksum = "32ac8da02677876d532745a130fc9d8e6edfa81a269b107c5b00829b91d8eb3c"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.171"
version = "1.0.183"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "389894603bd18c46fa56231694f8d827779c0951a667087194cf9de94ed24682"
checksum = "aafe972d60b0b9bee71a91b92fee2d4fb3c9d7e8f6b179aa99f27203d99a4816"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
]
[[package]]
name = "serde_json"
version = "1.0.102"
version = "1.0.104"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b5062a995d481b2308b6064e9af76011f2921c35f97b0468811ed9f6cd91dfed"
checksum = "076066c5f1078eac5b722a31827a8832fe108bed65dfa75e233c89f8206e976c"
dependencies = [
"itoa",
"ryu",
@ -2625,9 +2589,9 @@ dependencies = [
[[package]]
name = "serde_path_to_error"
version = "0.1.13"
version = "0.1.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8acc4422959dd87a76cb117c191dcbffc20467f06c9100b76721dab370f24d3a"
checksum = "4beec8bce849d58d06238cb50db2e1c417cfeafa4c63f692b15c82b7c80f8335"
dependencies = [
"itoa",
"serde",
@ -2687,9 +2651,9 @@ dependencies = [
[[package]]
name = "signal-hook"
version = "0.3.15"
version = "0.3.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "732768f1176d21d09e076c23a93123d40bba92d50c4058da34d45c8de8e682b9"
checksum = "8621587d4798caf8eb44879d42e56b9a93ea5dcd315a6487c357130095b62801"
dependencies = [
"libc",
"signal-hook-registry",
@ -2755,6 +2719,16 @@ dependencies = [
"winapi",
]
[[package]]
name = "socket2"
version = "0.5.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2538b18701741680e0322a2302176d3253a35388e2e62f172f64f4f16605f877"
dependencies = [
"libc",
"windows-sys 0.48.0",
]
[[package]]
name = "spin"
version = "0.5.2"
@ -2813,9 +2787,9 @@ dependencies = [
[[package]]
name = "syn"
version = "2.0.25"
version = "2.0.28"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "15e3fc8c0c74267e2df136e5e5fb656a464158aa57624053375eb9c8c6e25ae2"
checksum = "04361975b3f5e348b2189d8dc55bc942f278b2d482a6a0365de5bdd62d351567"
dependencies = [
"proc-macro2",
"quote",
@ -2830,9 +2804,9 @@ checksum = "2047c6ded9c721764247e62cd3b03c09ffc529b2ba5b10ec482ae507a4a70160"
[[package]]
name = "sysinfo"
version = "0.29.4"
version = "0.29.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "751e810399bba86e9326f5762b7f32ac5a085542df78da6a78d94e07d14d7c11"
checksum = "d10ed79c22663a35a255d289a7fdcb43559fc77ff15df5ce6c341809e7867528"
dependencies = [
"cfg-if",
"core-foundation-sys",
@ -2868,9 +2842,9 @@ dependencies = [
[[package]]
name = "tar"
version = "0.4.39"
version = "0.4.40"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ec96d2ffad078296368d46ff1cb309be1c23c513b4ab0e22a45de0185275ac96"
checksum = "b16afcea1f22891c49a00c751c7b63b2233284064f11a200fc624137c51e2ddb"
dependencies = [
"filetime",
"libc",
@ -2879,21 +2853,20 @@ dependencies = [
[[package]]
name = "tempfile"
version = "3.6.0"
version = "3.7.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "31c0432476357e58790aaa47a8efb0c5138f137343f3b5f23bd36a27e3b0a6d6"
checksum = "dc02fddf48964c42031a0b3fe0428320ecf3a73c401040fc0096f97794310651"
dependencies = [
"autocfg",
"cfg-if",
"fastrand",
"redox_syscall 0.3.5",
"rustix 0.37.23",
"rustix",
"windows-sys 0.48.0",
]
[[package]]
name = "text-generation-benchmark"
version = "1.0.0"
version = "1.0.1"
dependencies = [
"average",
"clap",
@ -2913,7 +2886,7 @@ dependencies = [
[[package]]
name = "text-generation-client"
version = "1.0.0"
version = "1.0.1"
dependencies = [
"futures",
"grpc-metadata",
@ -2929,7 +2902,7 @@ dependencies = [
[[package]]
name = "text-generation-launcher"
version = "1.0.0"
version = "1.0.1"
dependencies = [
"clap",
"ctrlc",
@ -2945,7 +2918,7 @@ dependencies = [
[[package]]
name = "text-generation-router"
version = "1.0.0"
version = "1.0.1"
dependencies = [
"async-stream",
"axum",
@ -2967,7 +2940,7 @@ dependencies = [
"thiserror",
"tokenizers",
"tokio",
"tower-http 0.4.1",
"tower-http 0.4.3",
"tracing",
"tracing-opentelemetry 0.19.0",
"tracing-subscriber",
@ -2978,22 +2951,22 @@ dependencies = [
[[package]]
name = "thiserror"
version = "1.0.43"
version = "1.0.44"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a35fc5b8971143ca348fa6df4f024d4d55264f3468c71ad1c2f365b0a4d58c42"
checksum = "611040a08a0439f8248d1990b111c95baa9c704c805fa1f62104b39655fd7f90"
dependencies = [
"thiserror-impl",
]
[[package]]
name = "thiserror-impl"
version = "1.0.43"
version = "1.0.44"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "463fe12d7993d3b327787537ce8dd4dfa058de32fc2b195ef3cde03dc4771e8f"
checksum = "090198534930841fab3a5d1bb637cde49e339654e606195f8d9c76eeb081dc96"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
]
[[package]]
@ -3008,10 +2981,11 @@ dependencies = [
[[package]]
name = "time"
version = "0.3.23"
version = "0.3.25"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "59e399c068f43a5d116fedaf73b203fa4f9c519f17e2b34f63221d3792f81446"
checksum = "b0fdd63d58b18d663fbdf70e049f00a22c8e42be082203be7f26589213cd75ea"
dependencies = [
"deranged",
"itoa",
"libc",
"num_threads",
@ -3028,9 +3002,9 @@ checksum = "7300fbefb4dadc1af235a9cef3737cea692a9d97e1b9cbcd4ebdae6f8868e6fb"
[[package]]
name = "time-macros"
version = "0.2.10"
version = "0.2.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "96ba15a897f3c86766b757e5ac7221554c6750054d74d5b28844fce5fb36a6c4"
checksum = "eb71511c991639bb078fd5bf97757e03914361c48100d52878b8e52b46fb92cd"
dependencies = [
"time-core",
]
@ -3052,9 +3026,9 @@ checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
[[package]]
name = "tokenizers"
version = "0.13.3"
version = "0.13.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5cf49017523bf0bc01c9966f172c5f120bbb7b96cccd1708772dd42e767fb9f5"
checksum = "aea68938177975ab09da68552b720eac941779ff386baceaf77e0f5f9cea645f"
dependencies = [
"aho-corasick 0.7.20",
"cached-path",
@ -3075,7 +3049,7 @@ dependencies = [
"rayon",
"rayon-cond",
"regex",
"regex-syntax 0.6.29",
"regex-syntax 0.7.4",
"reqwest",
"serde",
"serde_json",
@ -3088,11 +3062,10 @@ dependencies = [
[[package]]
name = "tokio"
version = "1.29.1"
version = "1.31.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "532826ff75199d5833b9d2c5fe410f29235e25704ee5f0ef599fb51c21f4a4da"
checksum = "40de3a2ba249dcb097e01be5e67a5ff53cf250397715a071a81543e8a832a920"
dependencies = [
"autocfg",
"backtrace",
"bytes",
"libc",
@ -3101,7 +3074,7 @@ dependencies = [
"parking_lot",
"pin-project-lite",
"signal-hook-registry",
"socket2",
"socket2 0.5.3",
"tokio-macros",
"windows-sys 0.48.0",
]
@ -3124,7 +3097,7 @@ checksum = "630bdcf245f78637c13ec01ffae6187cca34625e8c63150d424b59e55af2675e"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
]
[[package]]
@ -3288,11 +3261,11 @@ dependencies = [
[[package]]
name = "tower-http"
version = "0.4.1"
version = "0.4.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a8bd22a874a2d0b70452d5597b12c537331d49060824a95f49f108994f94aa4c"
checksum = "55ae70283aba8d2a8b411c695c437fe25b8b5e44e23e780662002fc72fb47a82"
dependencies = [
"bitflags 2.3.3",
"bitflags 2.4.0",
"bytes",
"futures-core",
"futures-util",
@ -3337,7 +3310,7 @@ checksum = "5f4f31f56159e98206da9efd823404b79b6ef3143b4a7ab76e67b1751b25a4ab"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
]
[[package]]
@ -3459,9 +3432,9 @@ checksum = "92888ba5573ff080736b3648696b70cafad7d250551175acbaa4e0385b3e1460"
[[package]]
name = "unicode-ident"
version = "1.0.10"
version = "1.0.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "22049a19f4a68748a168c0fc439f9516686aa045927ff767eca0a85101fb6e73"
checksum = "301abaae475aa91687eb82514b328ab47a211a533026cb25fc3e519b86adfc3c"
[[package]]
name = "unicode-normalization"
@ -3518,9 +3491,9 @@ dependencies = [
[[package]]
name = "urlencoding"
version = "2.1.2"
version = "2.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e8db7427f936968176eaa7cdf81b7f98b980b18495ec28f1b5791ac3bfe3eea9"
checksum = "daf8dba3b7eb870caf1ddeed7bc9d2a049f3cfdfae7cb521b087cc33ae4c49da"
[[package]]
name = "utf8parse"
@ -3530,9 +3503,9 @@ checksum = "711b9620af191e0cdc7468a8d14e709c3dcdb115b36f838e601583af800a370a"
[[package]]
name = "utoipa"
version = "3.4.0"
version = "3.4.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "520434cac5c98120177d5cc15be032703f6dca7d5ef82e725c798113b375000a"
checksum = "de634b7f8178c9c246c88ea251f3a0215c9a4d80778db2d7bd4423a78b5170ec"
dependencies = [
"indexmap 2.0.0",
"serde",
@ -3542,22 +3515,22 @@ dependencies = [
[[package]]
name = "utoipa-gen"
version = "3.4.1"
version = "3.4.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6e22e88a487b6e0374533871b79b1f5ded05671bd0936bd547eb42f82fb9060d"
checksum = "0fcba79cb3e5020d9bcc8313cd5aadaf51d6d54a6b3fd08c3d0360ae6b3c83d0"
dependencies = [
"proc-macro-error",
"proc-macro2",
"quote",
"regex",
"syn 2.0.25",
"syn 2.0.28",
]
[[package]]
name = "utoipa-swagger-ui"
version = "3.1.4"
version = "3.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4602d7100d3cfd8a086f30494e68532402ab662fa366c9d201d677e33cee138d"
checksum = "84614caa239fb25b2bb373a52859ffd94605ceb256eeb1d63436325cf81e3653"
dependencies = [
"axum",
"mime_guess",
@ -3646,7 +3619,7 @@ dependencies = [
"once_cell",
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
"wasm-bindgen-shared",
]
@ -3680,7 +3653,7 @@ checksum = "54681b18a46765f095758388f2d0cf16eb8d4169b639ab575a8f5693af210c7b"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.25",
"syn 2.0.28",
"wasm-bindgen-backend",
"wasm-bindgen-shared",
]
@ -3896,9 +3869,9 @@ dependencies = [
[[package]]
name = "xattr"
version = "0.2.3"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6d1526bbe5aaeb5eb06885f4d987bcdfa5e23187055de9b83fe00156a821fabc"
checksum = "f4686009f71ff3e5c4dbcf1a282d0a44db3f021ba69350cd42086b3e5f1c6985"
dependencies = [
"libc",
]

2
Cargo.toml
View File

@ -8,7 +8,7 @@ members = [
]
[workspace.package]
version = "1.0.0"
version = "1.0.1"
edition = "2021"
authors = ["Olivier Dehaene"]
homepage = "https://github.com/huggingface/text-generation-inference"

12
README.md
View File

@ -49,6 +49,9 @@ to power Hugging Chat, the Inference API and Inference Endpoint.
- Stop sequences
- Log probabilities
- Production ready (distributed tracing with Open Telemetry, Prometheus metrics)
- Custom Prompt Generation: Easily generate text by providing custom prompts to guide the model's output.
- Fine-tuning Support: Utilize fine-tuned models for specific tasks to achieve higher accuracy and performance.
## Optimized architectures
@ -83,11 +86,11 @@ The easiest way of getting started is using the official Docker container:
model=tiiuae/falcon-7b-instruct
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.0 --model-id $model
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 --model-id $model
```
**Note:** To use GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html). We also recommend using NVIDIA drivers with CUDA version 11.8 or higher.
**Note:** To use GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html). We also recommend using NVIDIA drivers with CUDA version 11.8 or higher. For running the Docker container on a machine with no GPUs or CUDA support, it is enough to remove the `--gpus all` flag and add `--disable-custom-kernels`, please note CPU is not the intended platform for this project, so performance might be subpar.
To see all options to serve your models (in the [code](https://github.com/huggingface/text-generation-inference/blob/main/launcher/src/main.rs) or in the cli:
To see all options to serve your models (in the [code](https://github.com/huggingface/text-generation-inference/blob/main/launcher/src/main.rs) or in the cli):
```
text-generation-launcher --help
```
@ -150,7 +153,7 @@ model=meta-llama/Llama-2-7b-chat-hf
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
token=<your cli READ token>
docker run --gpus all --shm-size 1g -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.0 --model-id $model
docker run --gpus all --shm-size 1g -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 --model-id $model
```
### A note on Shared Memory (shm)
@ -280,3 +283,4 @@ make integration-tests
TGI is also supported on the following AI hardware accelerators:
- *Habana first-gen Gaudi and Gaudi2:* checkout [here](https://github.com/huggingface/optimum-habana/tree/main/text-generation-inference) how to serve models with TGI on Gaudi and Gaudi2 with [Optimum Habana](https://huggingface.co/docs/optimum/habana/index)

4
benchmark/src/generation.rs
View File

@ -217,7 +217,5 @@ fn create_sequence(sequence_length: u32, tokenizer: Tokenizer) -> String {
// Truncate to sequence_length
encoding.truncate(sequence_length as usize, 0, TruncationDirection::Left);
// Decode
tokenizer
.decode(Vec::from(encoding.get_ids()), false)
.unwrap()
tokenizer.decode(encoding.get_ids(), false).unwrap()
}

2
docs/openapi.json
View File

@ -10,7 +10,7 @@
"name": "Apache 2.0",
"url": "https://www.apache.org/licenses/LICENSE-2.0"
},
"version": "1.0.0"
"version": "1.0.1"
},
"paths": {
"/": {

22
docs/source/basic_tutorials/consuming_tgi.md
View File

@ -1,6 +1,6 @@
# Consuming Text Generation Inference
There are many ways you can consume Text Generation Inference server in your applications. After launching, you can use the `/generate` route and make a `POST` request to get results from the server. You can also use the `/generate_stream` route if you want TGI to return a stram of tokens. You can make the requests using the tool of your preference, such as curl, Python or TypeScrpt. For a final end-to-end experience, we also open-sourced ChatUI, a chat interface for open-source models.
There are many ways you can consume Text Generation Inference server in your applications. After launching, you can use the `/generate` route and make a `POST` request to get results from the server. You can also use the `/generate_stream` route if you want TGI to return a stream of tokens. You can make the requests using the tool of your preference, such as curl, Python or TypeScrpt. For a final end-to-end experience, we also open-sourced ChatUI, a chat interface for open-source models.
## curl
@ -33,6 +33,24 @@ client = InferenceClient(model=URL_TO_ENDPOINT_SERVING_TGI)
client.text_generation(prompt="Write a code for snake game", model=URL_TO_ENDPOINT_SERVING_TGI)
```
To stream tokens in `InferenceClient`, simply pass `stream=True`. Another parameter you can use with TGI backend is `details`. You can get more details on generation (tokens, probabilities, etc.) by setting `details` to `True`. By default, `details` is set to `False`, and `text_generation` returns a string. If you pass `details=True` and `stream=True`, `text_generation` will return a `TextGenerationStreamResponse` which consists of the generated token, generated text, and details.
```python
output = client.text_generation(prompt="Meaning of life is", model=URL_OF_ENDPOINT, details=True)
print(output)
# TextGenerationResponse(generated_text=' a complex concept that is not always clear to the individual. It is a concept that is not always', details=Details(finish_reason=<FinishReason.Length: 'length'>, generated_tokens=20, seed=None, prefill=[], tokens=[Token(id=267, text=' a', logprob=-2.0723474, special=False), Token(id=11235, text=' complex', logprob=-3.1272552, special=False), Token(id=17908, text=' concept', logprob=-1.3632495, special=False),..))
```
You can see how to stream below.
```python
output = client.text_generation(prompt="Meaning of life is", model="http://localhost:3000/", stream=True, details=True)
print(next(iter(output)))
# TextGenerationStreamResponse(token=Token(id=267, text=' a', logprob=-2.0723474, special=False), generated_text=None, details=None)
```
You can check out the details of the function [here](https://huggingface.co/docs/huggingface_hub/main/en/package_reference/inference_client#huggingface_hub.InferenceClient.text_generation).
@ -49,7 +67,7 @@ To serve both ChatUI and TGI in same environment, simply add your own endpoints
}
```
TODO: Add screenshot
![ChatUI](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chatui_screen.png)
## API documentation

2
docs/source/basic_tutorials/gated_model_access.md
View File

@ -19,6 +19,6 @@ docker run --gpus all \
--shm-size 1g \
-e HUGGING_FACE_HUB_TOKEN=$token \
-p 8080:80 \
-v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.0 \
-v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 \
--model-id $model
```

67
docs/source/quicktour.md
View File

@ -8,7 +8,7 @@ Let's say you want to deploy [Falcon-7B Instruct](https://huggingface.co/tiiuae/
model=tiiuae/falcon-7b-instruct
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.0 --model-id $model
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 --model-id $model
```
<Tip warning={true}>
@ -17,15 +17,72 @@ To use GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvi
</Tip>
Once TGI is running, you can use the `generate` endpoint by doing requests. To learn more about how to query the endpoints, check the [Consuming TGI](./basic_tutorials/consuming_tgi) section.
Once TGI is running, you can use the `generate` endpoint by doing requests. To learn more about how to query the endpoints, check the [Consuming TGI](./basic_tutorials/consuming_tgi) section, where we show examples with utility libraries and UIs. Below you can see a simple snippet to query the endpoint.
```bash
curl 127.0.0.1:8080/generate -X POST -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":20}}' -H 'Content-Type: application/json'
<inferencesnippet>
<python>
```python
import requests
headers = {
"Content-Type": "application/json",
}
data = {
'inputs': 'What is Deep Learning?',
'parameters': {
'max_new_tokens': 20,
},
}
response = requests.post('http://127.0.0.1:8080/generate', headers=headers, json=data)
print(response.json())
# {'generated_text': '\n\nDeep Learning is a subset of Machine Learning that is concerned with the development of algorithms that can'}
```
</python>
<js>
```js
async function query() {
const response = await fetch(
'http://127.0.0.1:8080/generate',
{
method: 'POST',
headers: { 'Content-Type': 'application/json'},
body: JSON.stringify({
'inputs': 'What is Deep Learning?',
'parameters': {
'max_new_tokens': 20
}
})
}
);
}
query().then((response) => {
console.log(JSON.stringify(response));
});
/// {"generated_text":"\n\nDeep Learning is a subset of Machine Learning that is concerned with the development of algorithms that can"}
```
</js>
<curl>
```curl
curl 127.0.0.1:8080/generate \
-X POST \
-d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":20}}' \
-H 'Content-Type: application/json'
```
</curl>
</inferencesnippet>
<Tip>
To see all possible flags and options, you can use the `--help` flag. It's possible to configure the number of shards, quantization, generation parameters, and more.
To see all possible deploy flags and options, you can use the `--help` flag. It's possible to configure the number of shards, quantization, generation parameters, and more.
```bash
docker run ghcr.io/huggingface/text-generation-inference:1.0.0 --help

2
router/src/validation.rs
View File

@ -316,7 +316,7 @@ fn prepare_input(
// truncate encoding and decode new inputs
encoding.truncate(truncate, 0, TruncationDirection::Left);
let inputs = tokenizer
.decode(Vec::from(encoding.get_ids()), false)
.decode(encoding.get_ids(), false)
.map_err(|err| ValidationError::Tokenizer(err.to_string()))?;
(inputs, encoding.len())
}

3
server/.gitignore vendored
View File

@ -156,3 +156,6 @@ cython_debug/
transformers
safetensors
flash-attention/
flash-attention-v2/
vllm/

144
server/poetry.lock generated
View File

@ -2,13 +2,13 @@
[[package]]
name = "accelerate"
version = "0.19.0"
version = "0.20.3"
description = "Accelerate"
optional = false
python-versions = ">=3.7.0"
files = [
{file = "accelerate-0.19.0-py3-none-any.whl", hash = "sha256:2866b0bf9fff08f51e6384c95fa96725838b70f1988d1cce42e56b820d8a91dd"},
{file = "accelerate-0.19.0.tar.gz", hash = "sha256:84920226b9e642e453ef37593ee55b956b08d8200dea4087c546c34e26157e76"},
{file = "accelerate-0.20.3-py3-none-any.whl", hash = "sha256:147183e7a2215f7bd45a7af3b986a963daa8a61fa58b0912b9473049e011ad15"},
{file = "accelerate-0.20.3.tar.gz", hash = "sha256:79a896978c20dac270083d42bf033f4c9a80dcdd6b946f1ca92d8d6d0f0f5ba9"},
]
[package.dependencies]
@ -192,13 +192,13 @@ files = [
[[package]]
name = "bitsandbytes"
version = "0.40.2"
version = "0.41.1"
description = "k-bit optimizers and matrix multiplication routines."
optional = true
python-versions = "*"
files = [
{file = "bitsandbytes-0.40.2-py3-none-any.whl", hash = "sha256:f0ae26f40c9230c9add9e7c70a10a5ced36fb6deff39906aec1ce4fd25e6ddc0"},
{file = "bitsandbytes-0.40.2.tar.gz", hash = "sha256:808ac966272c63bccb2be6d77365275a4c28f1fa348d33656e670de3cab40fc4"},
{file = "bitsandbytes-0.41.1-py3-none-any.whl", hash = "sha256:b25228c27636367f222232ed4d1e1502eedd2064be215633734fb8ea0c1c65f4"},
{file = "bitsandbytes-0.41.1.tar.gz", hash = "sha256:b3f8e7e1e5f88d4813d10ebd4072034ba6a18eca7f0e255376f8320e5499032c"},
]
[[package]]
@ -1693,59 +1693,44 @@ use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
[[package]]
name = "safetensors"
version = "0.3.1"
version = "0.3.2"
description = "Fast and Safe Tensor serialization"
optional = false
python-versions = "*"
files = [
{file = "safetensors-0.3.1-cp310-cp310-macosx_10_11_x86_64.whl", hash = "sha256:2ae9b7dd268b4bae6624729dac86deb82104820e9786429b0583e5168db2f770"},
{file = "safetensors-0.3.1-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:08c85c1934682f1e2cd904d38433b53cd2a98245a7cc31f5689f9322a2320bbf"},
{file = "safetensors-0.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ba625c7af9e1c5d0d91cb83d2fba97d29ea69d4db2015d9714d24c7f6d488e15"},
{file = "safetensors-0.3.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b57d5890c619ec10d9f1b6426b8690d0c9c2868a90dc52f13fae6f6407ac141f"},
{file = "safetensors-0.3.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5c9f562ea696d50b95cadbeb1716dc476714a87792ffe374280c0835312cbfe2"},
{file = "safetensors-0.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5c115951b3a865ece8d98ee43882f2fd0a999c0200d6e6fec24134715ebe3b57"},
{file = "safetensors-0.3.1-cp310-cp310-win32.whl", hash = "sha256:118f8f7503ea312fc7af27e934088a1b589fb1eff5a7dea2cd1de6c71ee33391"},
{file = "safetensors-0.3.1-cp310-cp310-win_amd64.whl", hash = "sha256:54846eaae25fded28a7bebbb66be563cad221b4c80daee39e2f55df5e5e0266f"},
{file = "safetensors-0.3.1-cp311-cp311-macosx_10_11_universal2.whl", hash = "sha256:5af82e10946c4822506db0f29269f43147e889054704dde994d4e22f0c37377b"},
{file = "safetensors-0.3.1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:626c86dd1d930963c8ea7f953a3787ae85322551e3a5203ac731d6e6f3e18f44"},
{file = "safetensors-0.3.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:12e30677e6af1f4cc4f2832546e91dbb3b0aa7d575bfa473d2899d524e1ace08"},
{file = "safetensors-0.3.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d534b80bc8d39945bb902f34b0454773971fe9e5e1f2142af451759d7e52b356"},
{file = "safetensors-0.3.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ddd0ddd502cf219666e7d30f23f196cb87e829439b52b39f3e7da7918c3416df"},
{file = "safetensors-0.3.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:997a2cc14023713f423e6d16536d55cb16a3d72850f142e05f82f0d4c76d383b"},
{file = "safetensors-0.3.1-cp311-cp311-win32.whl", hash = "sha256:6ae9ca63d9e22f71ec40550207bd284a60a6b4916ae6ca12c85a8d86bf49e0c3"},
{file = "safetensors-0.3.1-cp311-cp311-win_amd64.whl", hash = "sha256:62aa7421ca455418423e35029524489480adda53e3f702453580180ecfebe476"},
{file = "safetensors-0.3.1-cp37-cp37m-macosx_10_11_x86_64.whl", hash = "sha256:6d54b3ed367b6898baab75dfd057c24f36ec64d3938ffff2af981d56bfba2f42"},
{file = "safetensors-0.3.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:262423aeda91117010f8c607889066028f680fbb667f50cfe6eae96f22f9d150"},
{file = "safetensors-0.3.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:10efe2513a8327fd628cea13167089588acc23093ba132aecfc536eb9a4560fe"},
{file = "safetensors-0.3.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:689b3d6a7ebce70ee9438267ee55ea89b575c19923876645e927d08757b552fe"},
{file = "safetensors-0.3.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:14cd9a87bc73ce06903e9f8ee8b05b056af6f3c9f37a6bd74997a16ed36ff5f4"},
{file = "safetensors-0.3.1-cp37-cp37m-win32.whl", hash = "sha256:a77cb39624480d5f143c1cc272184f65a296f573d61629eff5d495d2e0541d3e"},
{file = "safetensors-0.3.1-cp37-cp37m-win_amd64.whl", hash = "sha256:9eff3190bfbbb52eef729911345c643f875ca4dbb374aa6c559675cfd0ab73db"},
{file = "safetensors-0.3.1-cp38-cp38-macosx_10_11_x86_64.whl", hash = "sha256:05cbfef76e4daa14796db1bbb52072d4b72a44050c368b2b1f6fd3e610669a89"},
{file = "safetensors-0.3.1-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:c49061461f4a81e5ec3415070a3f135530834c89cbd6a7db7cd49e3cb9d9864b"},
{file = "safetensors-0.3.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22cf7e73ca42974f098ce0cf4dd8918983700b6b07a4c6827d50c8daefca776e"},
{file = "safetensors-0.3.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:04f909442d6223ff0016cd2e1b2a95ef8039b92a558014627363a2e267213f62"},
{file = "safetensors-0.3.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2c573c5a0d5d45791ae8c179e26d74aff86e719056591aa7edb3ca7be55bc961"},
{file = "safetensors-0.3.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6994043b12e717cf2a6ba69077ac41f0d3675b2819734f07f61819e854c622c7"},
{file = "safetensors-0.3.1-cp38-cp38-win32.whl", hash = "sha256:158ede81694180a0dbba59422bc304a78c054b305df993c0c6e39c6330fa9348"},
{file = "safetensors-0.3.1-cp38-cp38-win_amd64.whl", hash = "sha256:afdc725beff7121ea8d39a7339f5a6abcb01daa189ea56290b67fe262d56e20f"},
{file = "safetensors-0.3.1-cp39-cp39-macosx_10_11_x86_64.whl", hash = "sha256:cba910fcc9e5e64d32d62b837388721165e9c7e45d23bc3a38ad57694b77f40d"},
{file = "safetensors-0.3.1-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:a4f7dbfe7285573cdaddd85ef6fa84ebbed995d3703ab72d71257944e384612f"},
{file = "safetensors-0.3.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:54aed0802f9eaa83ca7b1cbb986bfb90b8e2c67b6a4bcfe245627e17dad565d4"},
{file = "safetensors-0.3.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:34b75a766f3cfc99fd4c33e329b76deae63f5f388e455d863a5d6e99472fca8e"},
{file = "safetensors-0.3.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1a0f31904f35dc14919a145b2d7a2d8842a43a18a629affe678233c4ea90b4af"},
{file = "safetensors-0.3.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dcf527ecc5f58907fd9031510378105487f318cc91ecdc5aee3c7cc8f46030a8"},
{file = "safetensors-0.3.1-cp39-cp39-win32.whl", hash = "sha256:e2f083112cf97aa9611e2a05cc170a2795eccec5f6ff837f4565f950670a9d83"},
{file = "safetensors-0.3.1-cp39-cp39-win_amd64.whl", hash = "sha256:5f4f614b8e8161cd8a9ca19c765d176a82b122fa3d3387b77862145bfe9b4e93"},
{file = "safetensors-0.3.1.tar.gz", hash = "sha256:571da56ff8d0bec8ae54923b621cda98d36dcef10feb36fd492c4d0c2cd0e869"},
{file = "safetensors-0.3.2-cp310-cp310-macosx_11_0_x86_64.whl", hash = "sha256:b6a66989075c2891d743153e8ba9ca84ee7232c8539704488f454199b8b8f84d"},
{file = "safetensors-0.3.2-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:670d6bc3a3b377278ce2971fa7c36ebc0a35041c4ea23b9df750a39380800195"},
{file = "safetensors-0.3.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cbb44e140bf2aeda98d9dde669dbec15f7b77f96a9274469b91a6cf4bcc5ec3b"},
{file = "safetensors-0.3.2-cp310-cp310-win32.whl", hash = "sha256:2961c1243fd0da46aa6a1c835305cc4595486f8ac64632a604d0eb5f2de76175"},
{file = "safetensors-0.3.2-cp310-cp310-win_amd64.whl", hash = "sha256:c813920482c337d1424d306e1b05824a38e3ef94303748a0a287dea7a8c4f805"},
{file = "safetensors-0.3.2-cp311-cp311-macosx_10_11_universal2.whl", hash = "sha256:707df34bd9b9047e97332136ad98e57028faeccdb9cfe1c3b52aba5964cc24bf"},
{file = "safetensors-0.3.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:becc5bb85b2947eae20ed23b407ebfd5277d9a560f90381fe2c42e6c043677ba"},
{file = "safetensors-0.3.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ada0fac127ff8fb04834da5c6d85a8077e6a1c9180a11251d96f8068db922a17"},
{file = "safetensors-0.3.2-cp311-cp311-win32.whl", hash = "sha256:155b82dbe2b0ebff18cde3f76b42b6d9470296e92561ef1a282004d449fa2b4c"},
{file = "safetensors-0.3.2-cp311-cp311-win_amd64.whl", hash = "sha256:a86428d196959619ce90197731be9391b5098b35100a7228ef4643957648f7f5"},
{file = "safetensors-0.3.2-cp37-cp37m-macosx_11_0_x86_64.whl", hash = "sha256:c1f8ab41ed735c5b581f451fd15d9602ff51aa88044bfa933c5fa4b1d0c644d1"},
{file = "safetensors-0.3.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3d7d70d48585fe8df00725aa788f2e64fd24a4c9ae07cd6be34f6859d0f89a9c"},
{file = "safetensors-0.3.2-cp37-cp37m-win32.whl", hash = "sha256:6ff59bc90cdc857f68b1023be9085fda6202bbe7f2fd67d06af8f976d6adcc10"},
{file = "safetensors-0.3.2-cp37-cp37m-win_amd64.whl", hash = "sha256:8b05c93da15fa911763a89281906ca333ed800ab0ef1c7ce53317aa1a2322f19"},
{file = "safetensors-0.3.2-cp38-cp38-macosx_11_0_x86_64.whl", hash = "sha256:8969cfd9e8d904e8d3c67c989e1bd9a95e3cc8980d4f95e4dcd43c299bb94253"},
{file = "safetensors-0.3.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aa98f49e95f02eb750d32c4947e7d5aa43883149ebd0414920866446525b70f0"},
{file = "safetensors-0.3.2-cp38-cp38-win32.whl", hash = "sha256:33409df5e28a83dc5cc5547a3ac17c0f1b13a1847b1eb3bc4b3be0df9915171e"},
{file = "safetensors-0.3.2-cp38-cp38-win_amd64.whl", hash = "sha256:e04a7cbbb3856159ab99e3adb14521544f65fcb8548cce773a1435a0f8d78d27"},
{file = "safetensors-0.3.2-cp39-cp39-macosx_11_0_x86_64.whl", hash = "sha256:7c864cf5dcbfb608c5378f83319c60cc9c97263343b57c02756b7613cd5ab4dd"},
{file = "safetensors-0.3.2-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:14e8c19d6dc51d4f70ee33c46aff04c8ba3f95812e74daf8036c24bc86e75cae"},
{file = "safetensors-0.3.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:87ff0024ef2e5722a79af24688ce4a430f70601d0cf712a744105ed4b8f67ba5"},
{file = "safetensors-0.3.2-cp39-cp39-win32.whl", hash = "sha256:827af9478b78977248ba93e2fd97ea307fb63f463f80cef4824460f8c2542a52"},
{file = "safetensors-0.3.2-cp39-cp39-win_amd64.whl", hash = "sha256:9b09f27c456efa301f98681ea14b12f81f2637889f6336223ccab71e42c34541"},
{file = "safetensors-0.3.2.tar.gz", hash = "sha256:2dbd34554ed3b99435a0e84df077108f5334c8336b5ed9cb8b6b98f7b10da2f6"},
]
[package.extras]
all = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "flax (>=0.6.3)", "h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "isort (>=5.5.4)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "numpy (>=1.21.6)", "paddlepaddle (>=2.4.1)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)", "tensorflow (>=2.11.0)", "torch (>=1.10)"]
dev = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "flax (>=0.6.3)", "h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "isort (>=5.5.4)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "numpy (>=1.21.6)", "paddlepaddle (>=2.4.1)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)", "tensorflow (>=2.11.0)", "torch (>=1.10)"]
all = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "flax (>=0.6.3)", "h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "isort (>=5.5.4)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "numpy (>=1.21.6)", "paddlepaddle (>=2.4.1)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)", "tensorflow (==2.11.0)", "torch (>=1.10)"]
dev = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "flax (>=0.6.3)", "h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "isort (>=5.5.4)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "numpy (>=1.21.6)", "paddlepaddle (>=2.4.1)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)", "tensorflow (==2.11.0)", "torch (>=1.10)"]
jax = ["flax (>=0.6.3)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)"]
numpy = ["numpy (>=1.21.6)"]
paddlepaddle = ["paddlepaddle (>=2.4.1)"]
pinned-tf = ["tensorflow (==2.11.0)"]
quality = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "isort (>=5.5.4)"]
tensorflow = ["tensorflow (>=2.11.0)"]
testing = ["h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "numpy (>=1.21.6)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)"]
@ -2013,13 +1998,13 @@ telegram = ["requests"]
[[package]]
name = "transformers"
version = "4.29.2"
version = "4.31.0"
description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
optional = false
python-versions = ">=3.7.0"
python-versions = ">=3.8.0"
files = [
{file = "transformers-4.29.2-py3-none-any.whl", hash = "sha256:0ef158b99bad6f4e6652a0d8655fbbe58b4cb788ce7040f320b5d29c7c810a75"},
{file = "transformers-4.29.2.tar.gz", hash = "sha256:ed9467661f459f1ce49461d83f18f3b36b6a37f306182dc2ba272935f3b93ebb"},
{file = "transformers-4.31.0-py3-none-any.whl", hash = "sha256:8487aab0195ce1c2a5ae189305118b9720daddbc7b688edb09ccd79e3b149f6b"},
{file = "transformers-4.31.0.tar.gz", hash = "sha256:4302fba920a1c24d3a429a29efff6a63eac03f3f3cf55b55927fc795d01cb273"},
]
[package.dependencies]
@ -2030,28 +2015,29 @@ packaging = ">=20.0"
pyyaml = ">=5.1"
regex = "!=2019.12.17"
requests = "*"
safetensors = ">=0.3.1"
tokenizers = ">=0.11.1,<0.11.3 || >0.11.3,<0.14"
tqdm = ">=4.27"
[package.extras]
accelerate = ["accelerate (>=0.19.0)"]
agents = ["Pillow", "accelerate (>=0.19.0)", "datasets (!=2.5.0)", "diffusers", "opencv-python", "sentencepiece (>=0.1.91,!=0.1.92)", "torch (>=1.9,!=1.12.0)"]
all = ["Pillow", "accelerate (>=0.19.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.6.9)", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "numba (<0.57.0)", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf (<=3.20.2)", "pyctcdecode (>=0.4.0)", "ray[tune]", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.4,<2.13)", "tensorflow-text (<2.13)", "tf2onnx", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision"]
audio = ["kenlm", "librosa", "numba (<0.57.0)", "phonemizer", "pyctcdecode (>=0.4.0)"]
accelerate = ["accelerate (>=0.20.3)"]
agents = ["Pillow (<10.0.0)", "accelerate (>=0.20.3)", "datasets (!=2.5.0)", "diffusers", "opencv-python", "sentencepiece (>=0.1.91,!=0.1.92)", "torch (>=1.9,!=1.12.0)"]
all = ["Pillow (<10.0.0)", "accelerate (>=0.20.3)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.2.8,!=0.3.2,<=0.4.13)", "jaxlib (>=0.1.65,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune]", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision"]
audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
codecarbon = ["codecarbon (==1.2.0)"]
deepspeed = ["accelerate (>=0.19.0)", "deepspeed (>=0.8.3)"]
deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.19.0)", "beautifulsoup4", "black (>=23.1,<24.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.8.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "optuna", "parameterized", "protobuf (<=3.20.2)", "psutil", "pytest", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "safetensors (>=0.2.1)", "sentencepiece (>=0.1.91,!=0.1.92)", "timeout-decorator"]
dev = ["GitPython (<3.1.19)", "Pillow", "accelerate (>=0.19.0)", "av (==9.2.0)", "beautifulsoup4", "black (>=23.1,<24.0)", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.6.9)", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "numba (<0.57.0)", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf (<=3.20.2)", "psutil", "pyctcdecode (>=0.4.0)", "pytest", "pytest-timeout", "pytest-xdist", "ray[tune]", "rhoknp (>=1.1.0)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "safetensors (>=0.2.1)", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorflow (>=2.4,<2.13)", "tensorflow-text (<2.13)", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
dev-tensorflow = ["GitPython (<3.1.19)", "Pillow", "beautifulsoup4", "black (>=23.1,<24.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "numba (<0.57.0)", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf (<=3.20.2)", "psutil", "pyctcdecode (>=0.4.0)", "pytest", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "safetensors (>=0.2.1)", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorflow (>=2.4,<2.13)", "tensorflow-text (<2.13)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "urllib3 (<2.0.0)"]
dev-torch = ["GitPython (<3.1.19)", "Pillow", "accelerate (>=0.19.0)", "beautifulsoup4", "black (>=23.1,<24.0)", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "numba (<0.57.0)", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf (<=3.20.2)", "psutil", "pyctcdecode (>=0.4.0)", "pytest", "pytest-timeout", "pytest-xdist", "ray[tune]", "rhoknp (>=1.1.0)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "safetensors (>=0.2.1)", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "timeout-decorator", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
docs = ["Pillow", "accelerate (>=0.19.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.6.9)", "hf-doc-builder", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "numba (<0.57.0)", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf (<=3.20.2)", "pyctcdecode (>=0.4.0)", "ray[tune]", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.4,<2.13)", "tensorflow-text (<2.13)", "tf2onnx", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision"]
deepspeed = ["accelerate (>=0.20.3)", "deepspeed (>=0.9.3)"]
deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.20.3)", "beautifulsoup4", "black (>=23.1,<24.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "optuna", "parameterized", "protobuf", "psutil", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "timeout-decorator"]
dev = ["GitPython (<3.1.19)", "Pillow (<10.0.0)", "accelerate (>=0.20.3)", "av (==9.2.0)", "beautifulsoup4", "black (>=23.1,<24.0)", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.2.8,!=0.3.2,<=0.4.13)", "jaxlib (>=0.1.65,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "ray[tune]", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorflow (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
dev-tensorflow = ["GitPython (<3.1.19)", "Pillow (<10.0.0)", "beautifulsoup4", "black (>=23.1,<24.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorflow (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "urllib3 (<2.0.0)"]
dev-torch = ["GitPython (<3.1.19)", "Pillow (<10.0.0)", "accelerate (>=0.20.3)", "beautifulsoup4", "black (>=23.1,<24.0)", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "ray[tune]", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "timeout-decorator", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
docs = ["Pillow (<10.0.0)", "accelerate (>=0.20.3)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "hf-doc-builder", "jax (>=0.2.8,!=0.3.2,<=0.4.13)", "jaxlib (>=0.1.65,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune]", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision"]
docs-specific = ["hf-doc-builder"]
fairscale = ["fairscale (>0.3)"]
flax = ["flax (>=0.4.1,<=0.6.9)", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "optax (>=0.0.8,<=0.1.4)"]
flax-speech = ["kenlm", "librosa", "numba (<0.57.0)", "phonemizer", "pyctcdecode (>=0.4.0)"]
flax = ["flax (>=0.4.1,<=0.7.0)", "jax (>=0.2.8,!=0.3.2,<=0.4.13)", "jaxlib (>=0.1.65,<=0.4.13)", "optax (>=0.0.8,<=0.1.4)"]
flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
ftfy = ["ftfy"]
integrations = ["optuna", "ray[tune]", "sigopt"]
ja = ["fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "rhoknp (>=1.1.0)", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)"]
ja = ["fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "rhoknp (>=1.1.0,<1.3.1)", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)"]
modelcreation = ["cookiecutter (==1.7.3)"]
natten = ["natten (>=0.14.6)"]
onnx = ["onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "tf2onnx"]
@ -2061,23 +2047,23 @@ quality = ["GitPython (<3.1.19)", "black (>=23.1,<24.0)", "datasets (!=2.5.0)",
ray = ["ray[tune]"]
retrieval = ["datasets (!=2.5.0)", "faiss-cpu"]
sagemaker = ["sagemaker (>=2.31.0)"]
sentencepiece = ["protobuf (<=3.20.2)", "sentencepiece (>=0.1.91,!=0.1.92)"]
serving = ["fastapi", "pydantic", "starlette", "uvicorn"]
sentencepiece = ["protobuf", "sentencepiece (>=0.1.91,!=0.1.92)"]
serving = ["fastapi", "pydantic (<2)", "starlette", "uvicorn"]
sigopt = ["sigopt"]
sklearn = ["scikit-learn"]
speech = ["kenlm", "librosa", "numba (<0.57.0)", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
testing = ["GitPython (<3.1.19)", "beautifulsoup4", "black (>=23.1,<24.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "parameterized", "protobuf (<=3.20.2)", "psutil", "pytest", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "safetensors (>=0.2.1)", "timeout-decorator"]
tf = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow (>=2.4,<2.13)", "tensorflow-text (<2.13)", "tf2onnx"]
tf-cpu = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow-cpu (>=2.4,<2.13)", "tensorflow-text (<2.13)", "tf2onnx"]
tf-speech = ["kenlm", "librosa", "numba (<0.57.0)", "phonemizer", "pyctcdecode (>=0.4.0)"]
speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
testing = ["GitPython (<3.1.19)", "beautifulsoup4", "black (>=23.1,<24.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "parameterized", "protobuf", "psutil", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "timeout-decorator"]
tf = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx"]
tf-cpu = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow-cpu (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx"]
tf-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
timm = ["timm"]
tokenizers = ["tokenizers (>=0.11.1,!=0.11.3,<0.14)"]
torch = ["accelerate (>=0.19.0)", "torch (>=1.9,!=1.12.0)"]
torch-speech = ["kenlm", "librosa", "numba (<0.57.0)", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
torch-vision = ["Pillow", "torchvision"]
torchhub = ["filelock", "huggingface-hub (>=0.14.1,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf (<=3.20.2)", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "tqdm (>=4.27)"]
torch = ["accelerate (>=0.20.3)", "torch (>=1.9,!=1.12.0)"]
torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
torch-vision = ["Pillow (<10.0.0)", "torchvision"]
torchhub = ["filelock", "huggingface-hub (>=0.14.1,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "tqdm (>=4.27)"]
video = ["av (==9.2.0)", "decord (==0.6.0)"]
vision = ["Pillow"]
vision = ["Pillow (<10.0.0)"]
[[package]]
name = "triton"
@ -2462,4 +2448,4 @@ quantize = ["accelerate", "datasets", "texttable"]
[metadata]
lock-version = "2.0"
python-versions = ">=3.9,<3.13"
content-hash = "2abb80833b678452cfc73464fc5b2e48d74b2672bd987240041a33c724a74000"
content-hash = "6b6dbd9e11bc2f71cd88e2ab50adce249a722fea02e7cdcf5fe1b94c7b997a57"

12
server/pyproject.toml
View File

@ -1,6 +1,6 @@
[tool.poetry]
name = "text-generation-server"
version = "1.0.0"
version = "1.0.1"
description = "Text Generation Inference Python gRPC Server"
authors = ["Olivier Dehaene <olivier@huggingface.co>"]
@ -15,18 +15,18 @@ grpcio-status = "^1.51.1"
grpcio-reflection = "^1.51.1"
grpc-interceptor = "^0.15.0"
typer = "^0.6.1"
accelerate = { version = "^0.19.0", optional = true }
bitsandbytes = { version = "^0.40.0", optional = true }
safetensors = "0.3.1"
accelerate = { version = "^0.20.0", optional = true }
bitsandbytes = { version = "^0.41.1", optional = true }
safetensors = "^0.3.2"
loguru = "^0.6.0"
opentelemetry-api = "^1.15.0"
opentelemetry-exporter-otlp = "^1.15.0"
opentelemetry-instrumentation-grpc = "^0.36b0"
hf-transfer = "^0.1.2"
sentencepiece = "^0.1.97"
tokenizers = "0.13.3"
tokenizers = "^0.13.3"
huggingface-hub = "^0.14.1"
transformers = "4.29.2"
transformers = "^4.31.0"
einops = "^0.6.1"
texttable = { version = "^1.6.7", optional = true }
datasets = { version = "^2.14.0", optional = true }

6
server/requirements.txt
View File

@ -1,6 +1,6 @@
--extra-index-url https://download.pytorch.org/whl/cu118
accelerate==0.19.0 ; python_version >= "3.9" and python_version < "3.13"
accelerate==0.20.3 ; python_version >= "3.9" and python_version < "3.13"
backoff==2.2.1 ; python_version >= "3.9" and python_version < "3.13"
certifi==2023.7.22 ; python_version >= "3.9" and python_version < "3.13"
charset-normalizer==3.2.0 ; python_version >= "3.9" and python_version < "3.13"
@ -42,7 +42,7 @@ psutil==5.9.5 ; python_version >= "3.9" and python_version < "3.13"
pyyaml==6.0.1 ; python_version >= "3.9" and python_version < "3.13"
regex==2023.6.3 ; python_version >= "3.9" and python_version < "3.13"
requests==2.31.0 ; python_version >= "3.9" and python_version < "3.13"
safetensors==0.3.1 ; python_version >= "3.9" and python_version < "3.13"
safetensors==0.3.2 ; python_version >= "3.9" and python_version < "3.13"
scipy==1.11.1 ; python_version >= "3.9" and python_version < "3.13"
sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13"
setuptools==68.0.0 ; python_version >= "3.9" and python_version < "3.13"
@ -50,7 +50,7 @@ sympy==1.12 ; python_version >= "3.9" and python_version < "3.13"
tokenizers==0.13.3 ; python_version >= "3.9" and python_version < "3.13"
torch==2.0.1+cu118 ; python_version >= "3.9" and python_version < "3.13"
tqdm==4.65.0 ; python_version >= "3.9" and python_version < "3.13"
transformers==4.29.2 ; python_version >= "3.9" and python_version < "3.13"
transformers==4.31.0 ; python_version >= "3.9" and python_version < "3.13"
triton==2.0.0 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.9" and python_version < "3.13"
typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
typing-extensions==4.7.1 ; python_version >= "3.9" and python_version < "3.13"

12
server/text_generation_server/cli.py
View File

@ -171,14 +171,14 @@ def download_weights(
for p in local_pt_files
]
try:
from transformers import AutoConfig
import transformers
import json
config = AutoConfig.from_pretrained(
model_id,
revision=revision,
)
architecture = config.architectures[0]
config_filename = hf_hub_download(model_id, revision=revision, filename="config.json")
with open(config_filename, "r") as f:
config = json.load(f)
architecture = config["architectures"][0]
class_ = getattr(transformers, architecture)

5
server/text_generation_server/models/flash_llama.py
View File

@ -2,7 +2,8 @@ import torch
import torch.distributed
from opentelemetry import trace
from transformers.models.llama import LlamaTokenizer, LlamaTokenizerFast
from transformers import AutoConfig, AutoTokenizer
from transformers.models.llama import LlamaTokenizer
from typing import Optional
from text_generation_server.models import FlashCausalLM
@ -44,7 +45,7 @@ class FlashLlama(FlashCausalLM):
trust_remote_code=trust_remote_code,
)
except Exception:
tokenizer = LlamaTokenizerFast.from_pretrained(
tokenizer = AutoTokenizer.from_pretrained(
model_id,
revision=revision,
padding_side="left",

2
server/text_generation_server/utils/layers.py
View File

@ -547,8 +547,6 @@ try:
self.inv_freq = _create_inv_freq(self.dim, newbase, self.inv_freq.device)
self._seq_len_cached = seqlen
t = torch.arange(seqlen, device=device, dtype=self.inv_freq.dtype)
if self.scaling_factor is not None:
t /= self.scaling_factor
# Don't do einsum, it converts fp32 to fp16
# freqs = torch.einsum("i,j->ij", t, self.inv_freq)