huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-09 19:34:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add distributed tracing

Browse Source
This commit is contained in:
OlivierDehaene 2023-02-09 15:07:08 +01:00
parent e520d5b349
commit 04015dfa90
6 changed files with 609 additions and 91 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

430
server/poetry.lock generated
View File

@ -39,6 +39,14 @@ tests = ["attrs[tests-no-zope]", "zope.interface"]
tests-no-zope = ["cloudpickle", "hypothesis", "mypy (>=0.971,<0.990)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"] tests-no-zope = ["cloudpickle", "hypothesis", "mypy (>=0.971,<0.990)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
tests_no_zope = ["cloudpickle", "hypothesis", "mypy (>=0.971,<0.990)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"] tests_no_zope = ["cloudpickle", "hypothesis", "mypy (>=0.971,<0.990)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
[[package]]
name = "backoff"
version = "2.2.1"
description = "Function decoration for backoff and retry"
category = "main"
optional = false
python-versions = ">=3.7,<4.0"
[[package]] [[package]]
name = "bitsandbytes" name = "bitsandbytes"
version = "0.35.4" version = "0.35.4"
@ -47,6 +55,22 @@ category = "main"
optional = false optional = false
python-versions = "*" python-versions = "*"
[[package]]
name = "certifi"
version = "2022.12.7"
description = "Python package for providing Mozilla's CA Bundle."
category = "main"
optional = false
python-versions = ">=3.6"
[[package]]
name = "charset-normalizer"
version = "3.0.1"
description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
category = "main"
optional = false
python-versions = "*"
[[package]] [[package]]
name = "click" name = "click"
version = "8.1.3" version = "8.1.3"
@ -66,6 +90,20 @@ category = "main"
optional = false optional = false
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7" python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
[[package]]
name = "Deprecated"
version = "1.2.13"
description = "Python @deprecated decorator to deprecate old python classes, functions or methods."
category = "main"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
[package.dependencies]
wrapt = ">=1.10,<2"
[package.extras]
dev = ["PyTest", "PyTest (<5)", "PyTest-Cov", "PyTest-Cov (<2.6)", "bump2version (<1)", "configparser (<5)", "importlib-metadata (<3)", "importlib-resources (<4)", "sphinx (<2)", "sphinxcontrib-websupport (<2)", "tox", "zipp (<2)"]
[[package]] [[package]]
name = "exceptiongroup" name = "exceptiongroup"
version = "1.1.0" version = "1.1.0"
@ -154,6 +192,14 @@ grpcio = ">=1.51.1"
protobuf = ">=4.21.6,<5.0dev" protobuf = ">=4.21.6,<5.0dev"
setuptools = "*" setuptools = "*"
[[package]]
name = "idna"
version = "3.4"
description = "Internationalized Domain Names in Applications (IDNA)"
category = "main"
optional = false
python-versions = ">=3.5"
[[package]] [[package]]
name = "iniconfig" name = "iniconfig"
version = "2.0.0" version = "2.0.0"
@ -233,6 +279,133 @@ python-versions = ">=3"
setuptools = "*" setuptools = "*"
wheel = "*" wheel = "*"
[[package]]
name = "opentelemetry-api"
version = "1.15.0"
description = "OpenTelemetry Python API"
category = "main"
optional = false
python-versions = ">=3.7"
[package.dependencies]
deprecated = ">=1.2.6"
setuptools = ">=16.0"
[[package]]
name = "opentelemetry-exporter-otlp"
version = "1.15.0"
description = "OpenTelemetry Collector Exporters"
category = "main"
optional = false
python-versions = ">=3.7"
[package.dependencies]
opentelemetry-exporter-otlp-proto-grpc = "1.15.0"
opentelemetry-exporter-otlp-proto-http = "1.15.0"
[[package]]
name = "opentelemetry-exporter-otlp-proto-grpc"
version = "1.15.0"
description = "OpenTelemetry Collector Protobuf over gRPC Exporter"
category = "main"
optional = false
python-versions = ">=3.7"
[package.dependencies]
backoff = {version = ">=1.10.0,<3.0.0", markers = "python_version >= \"3.7\""}
googleapis-common-protos = ">=1.52,<2.0"
grpcio = ">=1.0.0,<2.0.0"
opentelemetry-api = ">=1.12,<2.0"
opentelemetry-proto = "1.15.0"
opentelemetry-sdk = ">=1.12,<2.0"
[package.extras]
test = ["pytest-grpc"]
[[package]]
name = "opentelemetry-exporter-otlp-proto-http"
version = "1.15.0"
description = "OpenTelemetry Collector Protobuf over HTTP Exporter"
category = "main"
optional = false
python-versions = ">=3.7"
[package.dependencies]
backoff = {version = ">=1.10.0,<3.0.0", markers = "python_version >= \"3.7\""}
googleapis-common-protos = ">=1.52,<2.0"
opentelemetry-api = ">=1.12,<2.0"
opentelemetry-proto = "1.15.0"
opentelemetry-sdk = ">=1.12,<2.0"
requests = ">=2.7,<3.0"
[package.extras]
test = ["responses (==0.22.0)"]
[[package]]
name = "opentelemetry-instrumentation"
version = "0.36b0"
description = "Instrumentation Tools & Auto Instrumentation for OpenTelemetry Python"
category = "main"
optional = false
python-versions = ">=3.7"
[package.dependencies]
opentelemetry-api = ">=1.4,<2.0"
setuptools = ">=16.0"
wrapt = ">=1.0.0,<2.0.0"
[[package]]
name = "opentelemetry-instrumentation-grpc"
version = "0.36b0"
description = "OpenTelemetry gRPC instrumentation"
category = "main"
optional = false
python-versions = ">=3.7"
[package.dependencies]
opentelemetry-api = ">=1.12,<2.0"
opentelemetry-instrumentation = "0.36b0"
opentelemetry-sdk = ">=1.12,<2.0"
opentelemetry-semantic-conventions = "0.36b0"
wrapt = ">=1.0.0,<2.0.0"
[package.extras]
instruments = ["grpcio (>=1.27,<2.0)"]
test = ["opentelemetry-instrumentation-grpc[instruments]", "opentelemetry-sdk (>=1.12,<2.0)", "opentelemetry-test-utils (==0.36b0)", "protobuf (>=3.13,<4.0)"]
[[package]]
name = "opentelemetry-proto"
version = "1.15.0"
description = "OpenTelemetry Python Proto"
category = "main"
optional = false
python-versions = ">=3.7"
[package.dependencies]
protobuf = ">=3.19,<5.0"
[[package]]
name = "opentelemetry-sdk"
version = "1.15.0"
description = "OpenTelemetry Python SDK"
category = "main"
optional = false
python-versions = ">=3.7"
[package.dependencies]
opentelemetry-api = "1.15.0"
opentelemetry-semantic-conventions = "0.36b0"
setuptools = ">=16.0"
typing-extensions = ">=3.7.4"
[[package]]
name = "opentelemetry-semantic-conventions"
version = "0.36b0"
description = "OpenTelemetry Semantic Conventions"
category = "main"
optional = false
python-versions = ">=3.7"
[[package]] [[package]]
name = "packaging" name = "packaging"
version = "23.0" version = "23.0"
@ -300,6 +473,24 @@ category = "main"
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=3.6"
[[package]]
name = "requests"
version = "2.28.2"
description = "Python HTTP for Humans."
category = "main"
optional = false
python-versions = ">=3.7, <4"
[package.dependencies]
certifi = ">=2017.4.17"
charset-normalizer = ">=2,<4"
idna = ">=2.5,<4"
urllib3 = ">=1.21.1,<1.27"
[package.extras]
socks = ["PySocks (>=1.5.6,!=1.5.7)"]
use_chardet_on_py3 = ["chardet (>=3.0.2,<6)"]
[[package]] [[package]]
name = "safetensors" name = "safetensors"
version = "0.2.8" version = "0.2.8"
@ -382,6 +573,19 @@ category = "main"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
[[package]]
name = "urllib3"
version = "1.26.14"
description = "HTTP library with thread-safe connection pooling, file post, and more."
category = "main"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
[package.extras]
brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)", "brotlipy (>=0.6.0)"]
secure = ["certifi", "cryptography (>=1.3.4)", "idna (>=2.0.0)", "ipaddress", "pyOpenSSL (>=0.14)", "urllib3-secure-extra"]
socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
[[package]] [[package]]
name = "wheel" name = "wheel"
version = "0.38.4" version = "0.38.4"
@ -404,13 +608,21 @@ python-versions = ">=3.5"
[package.extras] [package.extras]
dev = ["black (>=19.3b0)", "pytest (>=4.6.2)"] dev = ["black (>=19.3b0)", "pytest (>=4.6.2)"]
[[package]]
name = "wrapt"
version = "1.14.1"
description = "Module for decorators, wrappers and monkey patching."
category = "main"
optional = false
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,>=2.7"
[extras] [extras]
bnb = ["bitsandbytes"] bnb = ["bitsandbytes"]
[metadata] [metadata]
lock-version = "1.1" lock-version = "1.1"
python-versions = "^3.9" python-versions = "^3.9"
content-hash = "c920067f39ade631d1022c0560c3a4336c82d8c28355509bdfff751bbcfc01cd" content-hash = "1a1fe3fd152c3b1a48908f4e3302b92278a3180d6fe5f39c27dc2b7b34d30dbf"
[metadata.files] [metadata.files]
accelerate = [ accelerate = [
@ -421,10 +633,108 @@ attrs = [
{file = "attrs-22.2.0-py3-none-any.whl", hash = "sha256:29e95c7f6778868dbd49170f98f8818f78f3dc5e0e37c0b1f474e3561b240836"}, {file = "attrs-22.2.0-py3-none-any.whl", hash = "sha256:29e95c7f6778868dbd49170f98f8818f78f3dc5e0e37c0b1f474e3561b240836"},
{file = "attrs-22.2.0.tar.gz", hash = "sha256:c9227bfc2f01993c03f68db37d1d15c9690188323c067c641f1a35ca58185f99"}, {file = "attrs-22.2.0.tar.gz", hash = "sha256:c9227bfc2f01993c03f68db37d1d15c9690188323c067c641f1a35ca58185f99"},
] ]
backoff = [
{file = "backoff-2.2.1-py3-none-any.whl", hash = "sha256:63579f9a0628e06278f7e47b7d7d5b6ce20dc65c5e96a6f3ca99a6adca0396e8"},
{file = "backoff-2.2.1.tar.gz", hash = "sha256:03f829f5bb1923180821643f8753b0502c3b682293992485b0eef2807afa5cba"},
]
bitsandbytes = [ bitsandbytes = [
{file = "bitsandbytes-0.35.4-py3-none-any.whl", hash = "sha256:201f168538ccfbd7594568a2f86c149cec8352782301076a15a783695ecec7fb"}, {file = "bitsandbytes-0.35.4-py3-none-any.whl", hash = "sha256:201f168538ccfbd7594568a2f86c149cec8352782301076a15a783695ecec7fb"},
{file = "bitsandbytes-0.35.4.tar.gz", hash = "sha256:b23db6b91cd73cb14faf9841a66bffa5c1722f9b8b57039ef2fb461ac22dd2a6"}, {file = "bitsandbytes-0.35.4.tar.gz", hash = "sha256:b23db6b91cd73cb14faf9841a66bffa5c1722f9b8b57039ef2fb461ac22dd2a6"},
] ]
certifi = [
{file = "certifi-2022.12.7-py3-none-any.whl", hash = "sha256:4ad3232f5e926d6718ec31cfc1fcadfde020920e278684144551c91769c7bc18"},
{file = "certifi-2022.12.7.tar.gz", hash = "sha256:35824b4c3a97115964b408844d64aa14db1cc518f6562e8d7261699d1350a9e3"},
]
charset-normalizer = [
{file = "charset-normalizer-3.0.1.tar.gz", hash = "sha256:ebea339af930f8ca5d7a699b921106c6e29c617fe9606fa7baa043c1cdae326f"},
{file = "charset_normalizer-3.0.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:88600c72ef7587fe1708fd242b385b6ed4b8904976d5da0893e31df8b3480cb6"},
{file = "charset_normalizer-3.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c75ffc45f25324e68ab238cb4b5c0a38cd1c3d7f1fb1f72b5541de469e2247db"},
{file = "charset_normalizer-3.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:db72b07027db150f468fbada4d85b3b2729a3db39178abf5c543b784c1254539"},
{file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:62595ab75873d50d57323a91dd03e6966eb79c41fa834b7a1661ed043b2d404d"},
{file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ff6f3db31555657f3163b15a6b7c6938d08df7adbfc9dd13d9d19edad678f1e8"},
{file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:772b87914ff1152b92a197ef4ea40efe27a378606c39446ded52c8f80f79702e"},
{file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:70990b9c51340e4044cfc394a81f614f3f90d41397104d226f21e66de668730d"},
{file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:292d5e8ba896bbfd6334b096e34bffb56161c81408d6d036a7dfa6929cff8783"},
{file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:2edb64ee7bf1ed524a1da60cdcd2e1f6e2b4f66ef7c077680739f1641f62f555"},
{file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:31a9ddf4718d10ae04d9b18801bd776693487cbb57d74cc3458a7673f6f34639"},
{file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:44ba614de5361b3e5278e1241fda3dc1838deed864b50a10d7ce92983797fa76"},
{file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:12db3b2c533c23ab812c2b25934f60383361f8a376ae272665f8e48b88e8e1c6"},
{file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:c512accbd6ff0270939b9ac214b84fb5ada5f0409c44298361b2f5e13f9aed9e"},
{file = "charset_normalizer-3.0.1-cp310-cp310-win32.whl", hash = "sha256:502218f52498a36d6bf5ea77081844017bf7982cdbe521ad85e64cabee1b608b"},
{file = "charset_normalizer-3.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:601f36512f9e28f029d9481bdaf8e89e5148ac5d89cffd3b05cd533eeb423b59"},
{file = "charset_normalizer-3.0.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:0298eafff88c99982a4cf66ba2efa1128e4ddaca0b05eec4c456bbc7db691d8d"},
{file = "charset_normalizer-3.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a8d0fc946c784ff7f7c3742310cc8a57c5c6dc31631269876a88b809dbeff3d3"},
{file = "charset_normalizer-3.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:87701167f2a5c930b403e9756fab1d31d4d4da52856143b609e30a1ce7160f3c"},
{file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:14e76c0f23218b8f46c4d87018ca2e441535aed3632ca134b10239dfb6dadd6b"},
{file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0c0a590235ccd933d9892c627dec5bc7511ce6ad6c1011fdf5b11363022746c1"},
{file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8c7fe7afa480e3e82eed58e0ca89f751cd14d767638e2550c77a92a9e749c317"},
{file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:79909e27e8e4fcc9db4addea88aa63f6423ebb171db091fb4373e3312cb6d603"},
{file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8ac7b6a045b814cf0c47f3623d21ebd88b3e8cf216a14790b455ea7ff0135d18"},
{file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:72966d1b297c741541ca8cf1223ff262a6febe52481af742036a0b296e35fa5a"},
{file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:f9d0c5c045a3ca9bedfc35dca8526798eb91a07aa7a2c0fee134c6c6f321cbd7"},
{file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:5995f0164fa7df59db4746112fec3f49c461dd6b31b841873443bdb077c13cfc"},
{file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:4a8fcf28c05c1f6d7e177a9a46a1c52798bfe2ad80681d275b10dcf317deaf0b"},
{file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:761e8904c07ad053d285670f36dd94e1b6ab7f16ce62b9805c475b7aa1cffde6"},
{file = "charset_normalizer-3.0.1-cp311-cp311-win32.whl", hash = "sha256:71140351489970dfe5e60fc621ada3e0f41104a5eddaca47a7acb3c1b851d6d3"},
{file = "charset_normalizer-3.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:9ab77acb98eba3fd2a85cd160851816bfce6871d944d885febf012713f06659c"},
{file = "charset_normalizer-3.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:84c3990934bae40ea69a82034912ffe5a62c60bbf6ec5bc9691419641d7d5c9a"},
{file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:74292fc76c905c0ef095fe11e188a32ebd03bc38f3f3e9bcb85e4e6db177b7ea"},
{file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c95a03c79bbe30eec3ec2b7f076074f4281526724c8685a42872974ef4d36b72"},
{file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f4c39b0e3eac288fedc2b43055cfc2ca7a60362d0e5e87a637beac5d801ef478"},
{file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df2c707231459e8a4028eabcd3cfc827befd635b3ef72eada84ab13b52e1574d"},
{file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:93ad6d87ac18e2a90b0fe89df7c65263b9a99a0eb98f0a3d2e079f12a0735837"},
{file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:59e5686dd847347e55dffcc191a96622f016bc0ad89105e24c14e0d6305acbc6"},
{file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:cd6056167405314a4dc3c173943f11249fa0f1b204f8b51ed4bde1a9cd1834dc"},
{file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:083c8d17153ecb403e5e1eb76a7ef4babfc2c48d58899c98fcaa04833e7a2f9a"},
{file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:f5057856d21e7586765171eac8b9fc3f7d44ef39425f85dbcccb13b3ebea806c"},
{file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:7eb33a30d75562222b64f569c642ff3dc6689e09adda43a082208397f016c39a"},
{file = "charset_normalizer-3.0.1-cp36-cp36m-win32.whl", hash = "sha256:95dea361dd73757c6f1c0a1480ac499952c16ac83f7f5f4f84f0658a01b8ef41"},
{file = "charset_normalizer-3.0.1-cp36-cp36m-win_amd64.whl", hash = "sha256:eaa379fcd227ca235d04152ca6704c7cb55564116f8bc52545ff357628e10602"},
{file = "charset_normalizer-3.0.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3e45867f1f2ab0711d60c6c71746ac53537f1684baa699f4f668d4c6f6ce8e14"},
{file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cadaeaba78750d58d3cc6ac4d1fd867da6fc73c88156b7a3212a3cd4819d679d"},
{file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:911d8a40b2bef5b8bbae2e36a0b103f142ac53557ab421dc16ac4aafee6f53dc"},
{file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:503e65837c71b875ecdd733877d852adbc465bd82c768a067badd953bf1bc5a3"},
{file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a60332922359f920193b1d4826953c507a877b523b2395ad7bc716ddd386d866"},
{file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:16a8663d6e281208d78806dbe14ee9903715361cf81f6d4309944e4d1e59ac5b"},
{file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:a16418ecf1329f71df119e8a65f3aa68004a3f9383821edcb20f0702934d8087"},
{file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:9d9153257a3f70d5f69edf2325357251ed20f772b12e593f3b3377b5f78e7ef8"},
{file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:02a51034802cbf38db3f89c66fb5d2ec57e6fe7ef2f4a44d070a593c3688667b"},
{file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:2e396d70bc4ef5325b72b593a72c8979999aa52fb8bcf03f701c1b03e1166918"},
{file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:11b53acf2411c3b09e6af37e4b9005cba376c872503c8f28218c7243582df45d"},
{file = "charset_normalizer-3.0.1-cp37-cp37m-win32.whl", hash = "sha256:0bf2dae5291758b6f84cf923bfaa285632816007db0330002fa1de38bfcb7154"},
{file = "charset_normalizer-3.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:2c03cc56021a4bd59be889c2b9257dae13bf55041a3372d3295416f86b295fb5"},
{file = "charset_normalizer-3.0.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:024e606be3ed92216e2b6952ed859d86b4cfa52cd5bc5f050e7dc28f9b43ec42"},
{file = "charset_normalizer-3.0.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:4b0d02d7102dd0f997580b51edc4cebcf2ab6397a7edf89f1c73b586c614272c"},
{file = "charset_normalizer-3.0.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:358a7c4cb8ba9b46c453b1dd8d9e431452d5249072e4f56cfda3149f6ab1405e"},
{file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:81d6741ab457d14fdedc215516665050f3822d3e56508921cc7239f8c8e66a58"},
{file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8b8af03d2e37866d023ad0ddea594edefc31e827fee64f8de5611a1dbc373174"},
{file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9cf4e8ad252f7c38dd1f676b46514f92dc0ebeb0db5552f5f403509705e24753"},
{file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e696f0dd336161fca9adbb846875d40752e6eba585843c768935ba5c9960722b"},
{file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c22d3fe05ce11d3671297dc8973267daa0f938b93ec716e12e0f6dee81591dc1"},
{file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:109487860ef6a328f3eec66f2bf78b0b72400280d8f8ea05f69c51644ba6521a"},
{file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:37f8febc8ec50c14f3ec9637505f28e58d4f66752207ea177c1d67df25da5aed"},
{file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:f97e83fa6c25693c7a35de154681fcc257c1c41b38beb0304b9c4d2d9e164479"},
{file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:a152f5f33d64a6be73f1d30c9cc82dfc73cec6477ec268e7c6e4c7d23c2d2291"},
{file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:39049da0ffb96c8cbb65cbf5c5f3ca3168990adf3551bd1dee10c48fce8ae820"},
{file = "charset_normalizer-3.0.1-cp38-cp38-win32.whl", hash = "sha256:4457ea6774b5611f4bed5eaa5df55f70abde42364d498c5134b7ef4c6958e20e"},
{file = "charset_normalizer-3.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:e62164b50f84e20601c1ff8eb55620d2ad25fb81b59e3cd776a1902527a788af"},
{file = "charset_normalizer-3.0.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:8eade758719add78ec36dc13201483f8e9b5d940329285edcd5f70c0a9edbd7f"},
{file = "charset_normalizer-3.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8499ca8f4502af841f68135133d8258f7b32a53a1d594aa98cc52013fff55678"},
{file = "charset_normalizer-3.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3fc1c4a2ffd64890aebdb3f97e1278b0cc72579a08ca4de8cd2c04799a3a22be"},
{file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:00d3ffdaafe92a5dc603cb9bd5111aaa36dfa187c8285c543be562e61b755f6b"},
{file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c2ac1b08635a8cd4e0cbeaf6f5e922085908d48eb05d44c5ae9eabab148512ca"},
{file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f6f45710b4459401609ebebdbcfb34515da4fc2aa886f95107f556ac69a9147e"},
{file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ae1de54a77dc0d6d5fcf623290af4266412a7c4be0b1ff7444394f03f5c54e3"},
{file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3b590df687e3c5ee0deef9fc8c547d81986d9a1b56073d82de008744452d6541"},
{file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:ab5de034a886f616a5668aa5d098af2b5385ed70142090e2a31bcbd0af0fdb3d"},
{file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:9cb3032517f1627cc012dbc80a8ec976ae76d93ea2b5feaa9d2a5b8882597579"},
{file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:608862a7bf6957f2333fc54ab4399e405baad0163dc9f8d99cb236816db169d4"},
{file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:0f438ae3532723fb6ead77e7c604be7c8374094ef4ee2c5e03a3a17f1fca256c"},
{file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:356541bf4381fa35856dafa6a965916e54bed415ad8a24ee6de6e37deccf2786"},
{file = "charset_normalizer-3.0.1-cp39-cp39-win32.whl", hash = "sha256:39cf9ed17fe3b1bc81f33c9ceb6ce67683ee7526e65fde1447c772afc54a1bb8"},
{file = "charset_normalizer-3.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:0a11e971ed097d24c534c037d298ad32c6ce81a45736d31e0ff0ad37ab437d59"},
{file = "charset_normalizer-3.0.1-py3-none-any.whl", hash = "sha256:7e189e2e1d3ed2f4aebabd2d5b0f931e883676e51c7624826e0a4e5fe8a0bf24"},
]
click = [ click = [
{file = "click-8.1.3-py3-none-any.whl", hash = "sha256:bb4d8133cb15a609f44e8213d9b391b0809795062913b383c62be0ee95b1db48"}, {file = "click-8.1.3-py3-none-any.whl", hash = "sha256:bb4d8133cb15a609f44e8213d9b391b0809795062913b383c62be0ee95b1db48"},
{file = "click-8.1.3.tar.gz", hash = "sha256:7682dc8afb30297001674575ea00d1814d808d6a36af415a82bd481d37ba7b8e"}, {file = "click-8.1.3.tar.gz", hash = "sha256:7682dc8afb30297001674575ea00d1814d808d6a36af415a82bd481d37ba7b8e"},
@ -433,6 +743,10 @@ colorama = [
{file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"}, {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
{file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"}, {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
] ]
Deprecated = [
{file = "Deprecated-1.2.13-py2.py3-none-any.whl", hash = "sha256:64756e3e14c8c5eea9795d93c524551432a0be75629f8f29e67ab8caf076c76d"},
{file = "Deprecated-1.2.13.tar.gz", hash = "sha256:43ac5335da90c31c24ba028af536a91d41d53f9e6901ddb021bcc572ce44e38d"},
]
exceptiongroup = [ exceptiongroup = [
{file = "exceptiongroup-1.1.0-py3-none-any.whl", hash = "sha256:327cbda3da756e2de031a3107b81ab7b3770a602c4d16ca618298c526f4bec1e"}, {file = "exceptiongroup-1.1.0-py3-none-any.whl", hash = "sha256:327cbda3da756e2de031a3107b81ab7b3770a602c4d16ca618298c526f4bec1e"},
{file = "exceptiongroup-1.1.0.tar.gz", hash = "sha256:bcb67d800a4497e1b404c2dd44fca47d3b7a5e5433dbab67f96c1a685cdfdf23"}, {file = "exceptiongroup-1.1.0.tar.gz", hash = "sha256:bcb67d800a4497e1b404c2dd44fca47d3b7a5e5433dbab67f96c1a685cdfdf23"},
@ -547,6 +861,10 @@ grpcio-tools = [
{file = "grpcio_tools-1.51.1-cp39-cp39-win32.whl", hash = "sha256:40ef70e8c5d0310dedff9af502b520b4c7e215bce94094527fb959150a0c594a"}, {file = "grpcio_tools-1.51.1-cp39-cp39-win32.whl", hash = "sha256:40ef70e8c5d0310dedff9af502b520b4c7e215bce94094527fb959150a0c594a"},
{file = "grpcio_tools-1.51.1-cp39-cp39-win_amd64.whl", hash = "sha256:15b8acf4eaa0ebe37e2f69108de49efd935b7abe9c7e58ba737490b99906aa76"}, {file = "grpcio_tools-1.51.1-cp39-cp39-win_amd64.whl", hash = "sha256:15b8acf4eaa0ebe37e2f69108de49efd935b7abe9c7e58ba737490b99906aa76"},
] ]
idna = [
{file = "idna-3.4-py3-none-any.whl", hash = "sha256:90b77e79eaa3eba6de819a0c442c0b4ceefc341a7a2ab77d7562bf49f425c5c2"},
{file = "idna-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"},
]
iniconfig = [ iniconfig = [
{file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"}, {file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"},
{file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"}, {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
@ -602,6 +920,42 @@ nvidia-cudnn-cu11 = [
{file = "nvidia_cudnn_cu11-8.5.0.96-2-py3-none-manylinux1_x86_64.whl", hash = "sha256:402f40adfc6f418f9dae9ab402e773cfed9beae52333f6d86ae3107a1b9527e7"}, {file = "nvidia_cudnn_cu11-8.5.0.96-2-py3-none-manylinux1_x86_64.whl", hash = "sha256:402f40adfc6f418f9dae9ab402e773cfed9beae52333f6d86ae3107a1b9527e7"},
{file = "nvidia_cudnn_cu11-8.5.0.96-py3-none-manylinux1_x86_64.whl", hash = "sha256:71f8111eb830879ff2836db3cccf03bbd735df9b0d17cd93761732ac50a8a108"}, {file = "nvidia_cudnn_cu11-8.5.0.96-py3-none-manylinux1_x86_64.whl", hash = "sha256:71f8111eb830879ff2836db3cccf03bbd735df9b0d17cd93761732ac50a8a108"},
] ]
opentelemetry-api = [
{file = "opentelemetry_api-1.15.0-py3-none-any.whl", hash = "sha256:e6c2d2e42140fd396e96edf75a7ceb11073f4efb4db87565a431cc9d0f93f2e0"},
{file = "opentelemetry_api-1.15.0.tar.gz", hash = "sha256:79ab791b4aaad27acc3dc3ba01596db5b5aac2ef75c70622c6038051d6c2cded"},
]
opentelemetry-exporter-otlp = [
{file = "opentelemetry_exporter_otlp-1.15.0-py3-none-any.whl", hash = "sha256:79f22748b6a54808a0448093dfa189c8490e729f67c134d4c992533d9393b33e"},
{file = "opentelemetry_exporter_otlp-1.15.0.tar.gz", hash = "sha256:4f7c49751d9720e2e726e13b0bb958ccade4e29122c305d92c033da432c8d2c5"},
]
opentelemetry-exporter-otlp-proto-grpc = [
{file = "opentelemetry_exporter_otlp_proto_grpc-1.15.0-py3-none-any.whl", hash = "sha256:c2a5492ba7d140109968135d641d06ce3c5bd73c50665f787526065d57d7fd1d"},
{file = "opentelemetry_exporter_otlp_proto_grpc-1.15.0.tar.gz", hash = "sha256:844f2a4bb9bcda34e4eb6fe36765e5031aacb36dc60ed88c90fc246942ea26e7"},
]
opentelemetry-exporter-otlp-proto-http = [
{file = "opentelemetry_exporter_otlp_proto_http-1.15.0-py3-none-any.whl", hash = "sha256:3ec2a02196c8a54bf5cbf7fe623a5238625638e83b6047a983bdf96e2bbb74c0"},
{file = "opentelemetry_exporter_otlp_proto_http-1.15.0.tar.gz", hash = "sha256:11b2c814249a49b22f6cca7a06b05701f561d577b747f3660dfd67b6eb9daf9c"},
]
opentelemetry-instrumentation = [
{file = "opentelemetry_instrumentation-0.36b0-py3-none-any.whl", hash = "sha256:83ba4ae7d5292b5b33e0f851cc5c76d8f91196b9b3527800fc13855c33383ac2"},
{file = "opentelemetry_instrumentation-0.36b0.tar.gz", hash = "sha256:e3ddac9b3b93408ef26c8ecbf38f717042977e16381bb4cd329a5b4cf16998cf"},
]
opentelemetry-instrumentation-grpc = [
{file = "opentelemetry_instrumentation_grpc-0.36b0-py3-none-any.whl", hash = "sha256:eaa246ed2083c97b13bab2555cb9d170e8433230a31476c4cab8a17fa03380a4"},
{file = "opentelemetry_instrumentation_grpc-0.36b0.tar.gz", hash = "sha256:dc89447c9eb6ea868970f6c13b4ffdac182cdd5a41dd215a0f5393ca6375be55"},
]
opentelemetry-proto = [
{file = "opentelemetry_proto-1.15.0-py3-none-any.whl", hash = "sha256:044b6d044b4d10530f250856f933442b8753a17f94ae37c207607f733fb9a844"},
{file = "opentelemetry_proto-1.15.0.tar.gz", hash = "sha256:9c4008e40ac8cab359daac283fbe7002c5c29c77ea2674ad5626a249e64e0101"},
]
opentelemetry-sdk = [
{file = "opentelemetry_sdk-1.15.0-py3-none-any.whl", hash = "sha256:555c533e9837766119bbccc7a80458c9971d853a6f1da683a2246cd5e53b4645"},
{file = "opentelemetry_sdk-1.15.0.tar.gz", hash = "sha256:98dbffcfeebcbff12c0c974292d6ea603180a145904cf838b1fe4d5c99078425"},
]
opentelemetry-semantic-conventions = [
{file = "opentelemetry_semantic_conventions-0.36b0-py3-none-any.whl", hash = "sha256:adc05635e87b9d3e007c9f530eed487fc3ef2177d02f82f674f28ebf9aff8243"},
{file = "opentelemetry_semantic_conventions-0.36b0.tar.gz", hash = "sha256:829dc221795467d98b773c04096e29be038d77526dc8d6ac76f546fb6279bf01"},
]
packaging = [ packaging = [
{file = "packaging-23.0-py3-none-any.whl", hash = "sha256:714ac14496c3e68c99c29b00845f7a2b85f3bb6f1078fd9f72fd20f0570002b2"}, {file = "packaging-23.0-py3-none-any.whl", hash = "sha256:714ac14496c3e68c99c29b00845f7a2b85f3bb6f1078fd9f72fd20f0570002b2"},
{file = "packaging-23.0.tar.gz", hash = "sha256:b6ad297f8907de0fa2fe1ccbd26fdaf387f5f47c7275fedf8cce89f99446cf97"}, {file = "packaging-23.0.tar.gz", hash = "sha256:b6ad297f8907de0fa2fe1ccbd26fdaf387f5f47c7275fedf8cce89f99446cf97"},
@ -688,6 +1042,10 @@ PyYAML = [
{file = "PyYAML-6.0-cp39-cp39-win_amd64.whl", hash = "sha256:b3d267842bf12586ba6c734f89d1f5b871df0273157918b0ccefa29deb05c21c"}, {file = "PyYAML-6.0-cp39-cp39-win_amd64.whl", hash = "sha256:b3d267842bf12586ba6c734f89d1f5b871df0273157918b0ccefa29deb05c21c"},
{file = "PyYAML-6.0.tar.gz", hash = "sha256:68fb519c14306fec9720a2a5b45bc9f0c8d1b9c72adf45c37baedfcd949c35a2"}, {file = "PyYAML-6.0.tar.gz", hash = "sha256:68fb519c14306fec9720a2a5b45bc9f0c8d1b9c72adf45c37baedfcd949c35a2"},
] ]
requests = [
{file = "requests-2.28.2-py3-none-any.whl", hash = "sha256:64299f4909223da747622c030b781c0d7811e359c37124b4bd368fb8c6518baa"},
{file = "requests-2.28.2.tar.gz", hash = "sha256:98b1b2782e3c6c4904938b84c0eb932721069dfdb9134313beff7c83c2df24bf"},
]
safetensors = [ safetensors = [
{file = "safetensors-0.2.8-cp310-cp310-macosx_10_11_x86_64.whl", hash = "sha256:8df8af89a0b6b535b47c077e33e5cd4941ef4b067e7c1dd1a05647dec0cf2eea"}, {file = "safetensors-0.2.8-cp310-cp310-macosx_10_11_x86_64.whl", hash = "sha256:8df8af89a0b6b535b47c077e33e5cd4941ef4b067e7c1dd1a05647dec0cf2eea"},
{file = "safetensors-0.2.8-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:9cabae651542b22d229b6439029fb4a3abc7868cb123af336b2877541ad9ab39"}, {file = "safetensors-0.2.8-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:9cabae651542b22d229b6439029fb4a3abc7868cb123af336b2877541ad9ab39"},
@ -769,6 +1127,10 @@ typing-extensions = [
{file = "typing_extensions-4.4.0-py3-none-any.whl", hash = "sha256:16fa4864408f655d35ec496218b85f79b3437c829e93320c7c9215ccfd92489e"}, {file = "typing_extensions-4.4.0-py3-none-any.whl", hash = "sha256:16fa4864408f655d35ec496218b85f79b3437c829e93320c7c9215ccfd92489e"},
{file = "typing_extensions-4.4.0.tar.gz", hash = "sha256:1511434bb92bf8dd198c12b1cc812e800d4181cfcb867674e0f8279cc93087aa"}, {file = "typing_extensions-4.4.0.tar.gz", hash = "sha256:1511434bb92bf8dd198c12b1cc812e800d4181cfcb867674e0f8279cc93087aa"},
] ]
urllib3 = [
{file = "urllib3-1.26.14-py2.py3-none-any.whl", hash = "sha256:75edcdc2f7d85b137124a6c3c9fc3933cdeaa12ecb9a6a959f22797a0feca7e1"},
{file = "urllib3-1.26.14.tar.gz", hash = "sha256:076907bf8fd355cde77728471316625a4d2f7e713c125f51953bb5b3eecf4f72"},
]
wheel = [ wheel = [
{file = "wheel-0.38.4-py3-none-any.whl", hash = "sha256:b60533f3f5d530e971d6737ca6d58681ee434818fab630c83a734bb10c083ce8"}, {file = "wheel-0.38.4-py3-none-any.whl", hash = "sha256:b60533f3f5d530e971d6737ca6d58681ee434818fab630c83a734bb10c083ce8"},
{file = "wheel-0.38.4.tar.gz", hash = "sha256:965f5259b566725405b05e7cf774052044b1ed30119b5d586b2703aafe8719ac"}, {file = "wheel-0.38.4.tar.gz", hash = "sha256:965f5259b566725405b05e7cf774052044b1ed30119b5d586b2703aafe8719ac"},
@ -777,3 +1139,69 @@ win32-setctime = [
{file = "win32_setctime-1.1.0-py3-none-any.whl", hash = "sha256:231db239e959c2fe7eb1d7dc129f11172354f98361c4fa2d6d2d7e278baa8aad"}, {file = "win32_setctime-1.1.0-py3-none-any.whl", hash = "sha256:231db239e959c2fe7eb1d7dc129f11172354f98361c4fa2d6d2d7e278baa8aad"},
{file = "win32_setctime-1.1.0.tar.gz", hash = "sha256:15cf5750465118d6929ae4de4eb46e8edae9a5634350c01ba582df868e932cb2"}, {file = "win32_setctime-1.1.0.tar.gz", hash = "sha256:15cf5750465118d6929ae4de4eb46e8edae9a5634350c01ba582df868e932cb2"},
] ]
wrapt = [
{file = "wrapt-1.14.1-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:1b376b3f4896e7930f1f772ac4b064ac12598d1c38d04907e696cc4d794b43d3"},
{file = "wrapt-1.14.1-cp27-cp27m-manylinux1_i686.whl", hash = "sha256:903500616422a40a98a5a3c4ff4ed9d0066f3b4c951fa286018ecdf0750194ef"},
{file = "wrapt-1.14.1-cp27-cp27m-manylinux1_x86_64.whl", hash = "sha256:5a9a0d155deafd9448baff28c08e150d9b24ff010e899311ddd63c45c2445e28"},
{file = "wrapt-1.14.1-cp27-cp27m-manylinux2010_i686.whl", hash = "sha256:ddaea91abf8b0d13443f6dac52e89051a5063c7d014710dcb4d4abb2ff811a59"},
{file = "wrapt-1.14.1-cp27-cp27m-manylinux2010_x86_64.whl", hash = "sha256:36f582d0c6bc99d5f39cd3ac2a9062e57f3cf606ade29a0a0d6b323462f4dd87"},
{file = "wrapt-1.14.1-cp27-cp27mu-manylinux1_i686.whl", hash = "sha256:7ef58fb89674095bfc57c4069e95d7a31cfdc0939e2a579882ac7d55aadfd2a1"},
{file = "wrapt-1.14.1-cp27-cp27mu-manylinux1_x86_64.whl", hash = "sha256:e2f83e18fe2f4c9e7db597e988f72712c0c3676d337d8b101f6758107c42425b"},
{file = "wrapt-1.14.1-cp27-cp27mu-manylinux2010_i686.whl", hash = "sha256:ee2b1b1769f6707a8a445162ea16dddf74285c3964f605877a20e38545c3c462"},
{file = "wrapt-1.14.1-cp27-cp27mu-manylinux2010_x86_64.whl", hash = "sha256:833b58d5d0b7e5b9832869f039203389ac7cbf01765639c7309fd50ef619e0b1"},
{file = "wrapt-1.14.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:80bb5c256f1415f747011dc3604b59bc1f91c6e7150bd7db03b19170ee06b320"},
{file = "wrapt-1.14.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:07f7a7d0f388028b2df1d916e94bbb40624c59b48ecc6cbc232546706fac74c2"},
{file = "wrapt-1.14.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:02b41b633c6261feff8ddd8d11c711df6842aba629fdd3da10249a53211a72c4"},
{file = "wrapt-1.14.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2fe803deacd09a233e4762a1adcea5db5d31e6be577a43352936179d14d90069"},
{file = "wrapt-1.14.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:257fd78c513e0fb5cdbe058c27a0624c9884e735bbd131935fd49e9fe719d310"},
{file = "wrapt-1.14.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:4fcc4649dc762cddacd193e6b55bc02edca674067f5f98166d7713b193932b7f"},
{file = "wrapt-1.14.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:11871514607b15cfeb87c547a49bca19fde402f32e2b1c24a632506c0a756656"},
{file = "wrapt-1.14.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:8ad85f7f4e20964db4daadcab70b47ab05c7c1cf2a7c1e51087bfaa83831854c"},
{file = "wrapt-1.14.1-cp310-cp310-win32.whl", hash = "sha256:a9a52172be0b5aae932bef82a79ec0a0ce87288c7d132946d645eba03f0ad8a8"},
{file = "wrapt-1.14.1-cp310-cp310-win_amd64.whl", hash = "sha256:6d323e1554b3d22cfc03cd3243b5bb815a51f5249fdcbb86fda4bf62bab9e164"},
{file = "wrapt-1.14.1-cp35-cp35m-manylinux1_i686.whl", hash = "sha256:43ca3bbbe97af00f49efb06e352eae40434ca9d915906f77def219b88e85d907"},
{file = "wrapt-1.14.1-cp35-cp35m-manylinux1_x86_64.whl", hash = "sha256:6b1a564e6cb69922c7fe3a678b9f9a3c54e72b469875aa8018f18b4d1dd1adf3"},
{file = "wrapt-1.14.1-cp35-cp35m-manylinux2010_i686.whl", hash = "sha256:00b6d4ea20a906c0ca56d84f93065b398ab74b927a7a3dbd470f6fc503f95dc3"},
{file = "wrapt-1.14.1-cp35-cp35m-manylinux2010_x86_64.whl", hash = "sha256:a85d2b46be66a71bedde836d9e41859879cc54a2a04fad1191eb50c2066f6e9d"},
{file = "wrapt-1.14.1-cp35-cp35m-win32.whl", hash = "sha256:dbcda74c67263139358f4d188ae5faae95c30929281bc6866d00573783c422b7"},
{file = "wrapt-1.14.1-cp35-cp35m-win_amd64.whl", hash = "sha256:b21bb4c09ffabfa0e85e3a6b623e19b80e7acd709b9f91452b8297ace2a8ab00"},
{file = "wrapt-1.14.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:9e0fd32e0148dd5dea6af5fee42beb949098564cc23211a88d799e434255a1f4"},
{file = "wrapt-1.14.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9736af4641846491aedb3c3f56b9bc5568d92b0692303b5a305301a95dfd38b1"},
{file = "wrapt-1.14.1-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5b02d65b9ccf0ef6c34cba6cf5bf2aab1bb2f49c6090bafeecc9cd81ad4ea1c1"},
{file = "wrapt-1.14.1-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:21ac0156c4b089b330b7666db40feee30a5d52634cc4560e1905d6529a3897ff"},
{file = "wrapt-1.14.1-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:9f3e6f9e05148ff90002b884fbc2a86bd303ae847e472f44ecc06c2cd2fcdb2d"},
{file = "wrapt-1.14.1-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:6e743de5e9c3d1b7185870f480587b75b1cb604832e380d64f9504a0535912d1"},
{file = "wrapt-1.14.1-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:d79d7d5dc8a32b7093e81e97dad755127ff77bcc899e845f41bf71747af0c569"},
{file = "wrapt-1.14.1-cp36-cp36m-win32.whl", hash = "sha256:81b19725065dcb43df02b37e03278c011a09e49757287dca60c5aecdd5a0b8ed"},
{file = "wrapt-1.14.1-cp36-cp36m-win_amd64.whl", hash = "sha256:b014c23646a467558be7da3d6b9fa409b2c567d2110599b7cf9a0c5992b3b471"},
{file = "wrapt-1.14.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:88bd7b6bd70a5b6803c1abf6bca012f7ed963e58c68d76ee20b9d751c74a3248"},
{file = "wrapt-1.14.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b5901a312f4d14c59918c221323068fad0540e34324925c8475263841dbdfe68"},
{file = "wrapt-1.14.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d77c85fedff92cf788face9bfa3ebaa364448ebb1d765302e9af11bf449ca36d"},
{file = "wrapt-1.14.1-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d649d616e5c6a678b26d15ece345354f7c2286acd6db868e65fcc5ff7c24a77"},
{file = "wrapt-1.14.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:7d2872609603cb35ca513d7404a94d6d608fc13211563571117046c9d2bcc3d7"},
{file = "wrapt-1.14.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:ee6acae74a2b91865910eef5e7de37dc6895ad96fa23603d1d27ea69df545015"},
{file = "wrapt-1.14.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:2b39d38039a1fdad98c87279b48bc5dce2c0ca0d73483b12cb72aa9609278e8a"},
{file = "wrapt-1.14.1-cp37-cp37m-win32.whl", hash = "sha256:60db23fa423575eeb65ea430cee741acb7c26a1365d103f7b0f6ec412b893853"},
{file = "wrapt-1.14.1-cp37-cp37m-win_amd64.whl", hash = "sha256:709fe01086a55cf79d20f741f39325018f4df051ef39fe921b1ebe780a66184c"},
{file = "wrapt-1.14.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:8c0ce1e99116d5ab21355d8ebe53d9460366704ea38ae4d9f6933188f327b456"},
{file = "wrapt-1.14.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:e3fb1677c720409d5f671e39bac6c9e0e422584e5f518bfd50aa4cbbea02433f"},
{file = "wrapt-1.14.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:642c2e7a804fcf18c222e1060df25fc210b9c58db7c91416fb055897fc27e8cc"},
{file = "wrapt-1.14.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7b7c050ae976e286906dd3f26009e117eb000fb2cf3533398c5ad9ccc86867b1"},
{file = "wrapt-1.14.1-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ef3f72c9666bba2bab70d2a8b79f2c6d2c1a42a7f7e2b0ec83bb2f9e383950af"},
{file = "wrapt-1.14.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:01c205616a89d09827986bc4e859bcabd64f5a0662a7fe95e0d359424e0e071b"},
{file = "wrapt-1.14.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:5a0f54ce2c092aaf439813735584b9537cad479575a09892b8352fea5e988dc0"},
{file = "wrapt-1.14.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:2cf71233a0ed05ccdabe209c606fe0bac7379fdcf687f39b944420d2a09fdb57"},
{file = "wrapt-1.14.1-cp38-cp38-win32.whl", hash = "sha256:aa31fdcc33fef9eb2552cbcbfee7773d5a6792c137b359e82879c101e98584c5"},
{file = "wrapt-1.14.1-cp38-cp38-win_amd64.whl", hash = "sha256:d1967f46ea8f2db647c786e78d8cc7e4313dbd1b0aca360592d8027b8508e24d"},
{file = "wrapt-1.14.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:3232822c7d98d23895ccc443bbdf57c7412c5a65996c30442ebe6ed3df335383"},
{file = "wrapt-1.14.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:988635d122aaf2bdcef9e795435662bcd65b02f4f4c1ae37fbee7401c440b3a7"},
{file = "wrapt-1.14.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9cca3c2cdadb362116235fdbd411735de4328c61425b0aa9f872fd76d02c4e86"},
{file = "wrapt-1.14.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d52a25136894c63de15a35bc0bdc5adb4b0e173b9c0d07a2be9d3ca64a332735"},
{file = "wrapt-1.14.1-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:40e7bc81c9e2b2734ea4bc1aceb8a8f0ceaac7c5299bc5d69e37c44d9081d43b"},
{file = "wrapt-1.14.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:b9b7a708dd92306328117d8c4b62e2194d00c365f18eff11a9b53c6f923b01e3"},
{file = "wrapt-1.14.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:6a9a25751acb379b466ff6be78a315e2b439d4c94c1e99cb7266d40a537995d3"},
{file = "wrapt-1.14.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:34aa51c45f28ba7f12accd624225e2b1e5a3a45206aa191f6f9aac931d9d56fe"},
{file = "wrapt-1.14.1-cp39-cp39-win32.whl", hash = "sha256:dee0ce50c6a2dd9056c20db781e9c1cfd33e77d2d569f5d1d9321c641bb903d5"},
{file = "wrapt-1.14.1-cp39-cp39-win_amd64.whl", hash = "sha256:dee60e1de1898bde3b238f18340eec6148986da0455d8ba7848d50470a7a32fb"},
{file = "wrapt-1.14.1.tar.gz", hash = "sha256:380a85cf89e0e69b7cfbe2ea9f765f004ff419f34194018a6827ac0e3edfed4d"},
]

3
server/pyproject.toml
View File

@ -19,6 +19,9 @@ accelerate = "^0.15.0"
bitsandbytes = "^0.35.1" bitsandbytes = "^0.35.1"
safetensors = "^0.2.4" safetensors = "^0.2.4"
loguru = "^0.6.0" loguru = "^0.6.0"
opentelemetry-api = "^1.15.0"
opentelemetry-exporter-otlp = "^1.15.0"
opentelemetry-instrumentation-grpc = "^0.36b0"
[tool.poetry.extras] [tool.poetry.extras]
bnb = ["bitsandbytes"] bnb = ["bitsandbytes"]

27
server/text_generation/cli.py
View File

@ -7,6 +7,7 @@ from loguru import logger
from typing import Optional from typing import Optional
from text_generation import server, utils from text_generation import server, utils
from text_generation.tracing import setup_tracing
app = typer.Typer() app = typer.Typer()
@ -18,20 +19,10 @@ def serve(
sharded: bool = False, sharded: bool = False,
quantize: bool = False, quantize: bool = False,
uds_path: Path = "/tmp/text-generation", uds_path: Path = "/tmp/text-generation",
otlp_endpoint: Optional[str] = None,
logger_level: str = "INFO", logger_level: str = "INFO",
json_output: bool = False, json_output: bool = False,
): ):
# Remove default handler
logger.remove()
logger.add(
sys.stdout,
format="{message}",
filter="text_generation",
level=logger_level,
serialize=json_output,
backtrace=True,
diagnose=False,
)
if sharded: if sharded:
assert ( assert (
os.getenv("RANK", None) is not None os.getenv("RANK", None) is not None
@ -46,6 +37,20 @@ def serve(
os.getenv("MASTER_PORT", None) is not None os.getenv("MASTER_PORT", None) is not None
), "MASTER_PORT must be set when sharded is True" ), "MASTER_PORT must be set when sharded is True"
# Remove default handler
logger.remove()
logger.add(
sys.stdout,
format="{message}",
filter="text_generation",
level=logger_level,
serialize=json_output,
backtrace=True,
diagnose=False,
)
# Setup OpenTelemetry distributed tracing
setup_tracing(shard=os.getenv("RANK", 0), otlp_endpoint=otlp_endpoint)
server.serve(model_id, revision, sharded, quantize, uds_path) server.serve(model_id, revision, sharded, quantize, uds_path)

162
server/text_generation/models/causal_lm.py
View File

@ -1,6 +1,7 @@
import torch import torch
from dataclasses import dataclass from dataclasses import dataclass
from opentelemetry import trace
from transformers import AutoTokenizer, AutoModelForCausalLM, PreTrainedTokenizerBase from transformers import AutoTokenizer, AutoModelForCausalLM, PreTrainedTokenizerBase
from typing import Optional, Tuple, List, Type from typing import Optional, Tuple, List, Type
@ -9,6 +10,7 @@ from text_generation.models.types import Batch, PrefillTokens, Generation, Gener
from text_generation.pb import generate_pb2 from text_generation.pb import generate_pb2
from text_generation.utils import NextTokenChooser, StoppingCriteria, Sampling from text_generation.utils import NextTokenChooser, StoppingCriteria, Sampling
tracer = trace.get_tracer(__name__)
@dataclass @dataclass
class CausalLMBatch(Batch): class CausalLMBatch(Batch):
@ -94,6 +96,7 @@ class CausalLMBatch(Batch):
) )
@classmethod @classmethod
@tracer.start_as_current_span("concatenate")
def concatenate(cls, batches: List["CausalLMBatch"]) -> "CausalLMBatch": def concatenate(cls, batches: List["CausalLMBatch"]) -> "CausalLMBatch":
# Used for padding # Used for padding
total_batch_size = sum(batch.size for batch in batches) total_batch_size = sum(batch.size for batch in batches)
@ -273,6 +276,7 @@ class CausalLM(Model):
generated_ids, skip_special_tokens=True, cleanup_tokenization_spaces=False generated_ids, skip_special_tokens=True, cleanup_tokenization_spaces=False
) )
@tracer.start_as_current_span("forward")
def forward( def forward(
self, input_ids, attention_mask, position_ids, past_key_values: Optional = None self, input_ids, attention_mask, position_ids, past_key_values: Optional = None
) -> Tuple[torch.Tensor, List[Tuple[torch.Tensor, torch.Tensor]]]: ) -> Tuple[torch.Tensor, List[Tuple[torch.Tensor, torch.Tensor]]]:
@ -286,6 +290,7 @@ class CausalLM(Model):
) )
return outputs.logits, outputs.past_key_values return outputs.logits, outputs.past_key_values
@tracer.start_as_current_span("generate_token")
def generate_token( def generate_token(
self, batch: CausalLMBatch self, batch: CausalLMBatch
) -> Tuple[List[Generation], Optional[CausalLMBatch]]: ) -> Tuple[List[Generation], Optional[CausalLMBatch]]:
@ -321,92 +326,93 @@ class CausalLM(Model):
batch.all_input_ids, batch.all_input_ids,
) )
# For each member of the batch with tracer.start_as_current_span("post_processing"):
for i, ( # For each member of the batch
request, for i, (
input_length, request,
logits, input_length,
next_token_chooser, logits,
stopping_criteria, next_token_chooser,
all_input_ids, stopping_criteria,
) in enumerate(iterator): all_input_ids,
# Select next token ) in enumerate(iterator):
tokens, logprobs = next_token_chooser(all_input_ids.view(1, -1), logits) # Select next token
next_token_id = tokens[-1].view(1, 1) tokens, logprobs = next_token_chooser(all_input_ids.view(1, -1), logits)
next_token_id = tokens[-1].view(1, 1)
# Append next token to all tokens # Append next token to all tokens
all_input_ids = torch.cat([all_input_ids, next_token_id]) all_input_ids = torch.cat([all_input_ids, next_token_id])
new_input_length = input_length + 1 new_input_length = input_length + 1
# Generated token # Generated token
next_token_logprob = logprobs[-1, next_token_id] next_token_logprob = logprobs[-1, next_token_id]
next_token_id_squeezed = next_token_id.squeeze() next_token_id_squeezed = next_token_id.squeeze()
next_token_text = self.tokenizer.decode( next_token_text = self.tokenizer.decode(
next_token_id_squeezed, next_token_id_squeezed,
clean_up_tokenization_spaces=False,
skip_special_tokens=False,
)
# Evaluate stopping criteria
stop, reason = stopping_criteria(
next_token_id_squeezed,
next_token_text,
)
if stop:
# Decode generated tokens
output_text = self.decode(
all_input_ids[-stopping_criteria.current_tokens :, 0]
)
# Get seed
if isinstance(next_token_chooser.choice, Sampling):
seed = next_token_chooser.choice.seed
else:
seed = None
generated_text = GeneratedText(
output_text, stopping_criteria.current_tokens, reason, seed
)
else:
# Keep request in the batch
generated_text = None
next_batch_keep_indices.append(i)
next_batch_input_ids.append(next_token_id)
next_batch_all_input_ids.append(all_input_ids)
next_batch_size += 1
next_batch_input_lengths.append(new_input_length)
next_batch_max_sequence_length = max(
next_batch_max_sequence_length, new_input_length
)
# Prefill
if stopping_criteria.current_tokens == 1:
# Remove generated token to only have prefill and add nan for first prompt token
prefill_logprobs = [float("nan")] + logprobs.gather(
1, all_input_ids[1:]
).squeeze(1)[-new_input_length:-1].tolist()
prefill_token_ids = all_input_ids[-new_input_length:-1]
prefill_texts = self.tokenizer.batch_decode(
prefill_token_ids,
clean_up_tokenization_spaces=False, clean_up_tokenization_spaces=False,
skip_special_tokens=False, skip_special_tokens=False,
) )
prefill_tokens = PrefillTokens(
prefill_token_ids, prefill_logprobs, prefill_texts # Evaluate stopping criteria
stop, reason = stopping_criteria(
next_token_id_squeezed,
next_token_text,
) )
else:
prefill_tokens = None
generation = Generation( if stop:
request.id, # Decode generated tokens
prefill_tokens, output_text = self.decode(
next_token_id_squeezed, all_input_ids[-stopping_criteria.current_tokens :, 0]
next_token_logprob, )
next_token_text, # Get seed
generated_text, if isinstance(next_token_chooser.choice, Sampling):
) seed = next_token_chooser.choice.seed
else:
seed = None
generations.append(generation) generated_text = GeneratedText(
output_text, stopping_criteria.current_tokens, reason, seed
)
else:
# Keep request in the batch
generated_text = None
next_batch_keep_indices.append(i)
next_batch_input_ids.append(next_token_id)
next_batch_all_input_ids.append(all_input_ids)
next_batch_size += 1
next_batch_input_lengths.append(new_input_length)
next_batch_max_sequence_length = max(
next_batch_max_sequence_length, new_input_length
)
# Prefill
if stopping_criteria.current_tokens == 1:
# Remove generated token to only have prefill and add nan for first prompt token
prefill_logprobs = [float("nan")] + logprobs.gather(
1, all_input_ids[1:]
).squeeze(1)[-new_input_length:-1].tolist()
prefill_token_ids = all_input_ids[-new_input_length:-1]
prefill_texts = self.tokenizer.batch_decode(
prefill_token_ids,
clean_up_tokenization_spaces=False,
skip_special_tokens=False,
)
prefill_tokens = PrefillTokens(
prefill_token_ids, prefill_logprobs, prefill_texts
)
else:
prefill_tokens = None
generation = Generation(
request.id,
prefill_tokens,
next_token_id_squeezed,
next_token_logprob,
next_token_text,
generated_text,
)
generations.append(generation)
# We finished all generations in the batch; there is no next batch # We finished all generations in the batch; there is no next batch
if not next_batch_keep_indices: if not next_batch_keep_indices:

3
server/text_generation/server.py
View File

@ -13,6 +13,7 @@ from text_generation.cache import Cache
from text_generation.interceptor import ExceptionInterceptor from text_generation.interceptor import ExceptionInterceptor
from text_generation.models import Model, get_model from text_generation.models import Model, get_model
from text_generation.pb import generate_pb2_grpc, generate_pb2 from text_generation.pb import generate_pb2_grpc, generate_pb2
from text_generation.tracing import OpenTelemetryAioServerInterceptorUnix
class TextGenerationService(generate_pb2_grpc.TextGenerationServiceServicer): class TextGenerationService(generate_pb2_grpc.TextGenerationServiceServicer):
@ -100,7 +101,7 @@ def serve(
logger.exception("Error when initializing model") logger.exception("Error when initializing model")
raise raise
server = aio.server(interceptors=[ExceptionInterceptor()]) server = aio.server(interceptors=[ExceptionInterceptor(), OpenTelemetryAioServerInterceptorUnix()])
generate_pb2_grpc.add_TextGenerationServiceServicer_to_server( generate_pb2_grpc.add_TextGenerationServiceServicer_to_server(
TextGenerationService(model, Cache(), server_urls), server TextGenerationService(model, Cache(), server_urls), server
) )

75
server/text_generation/tracing.py Normal file
View File

@ -0,0 +1,75 @@
import grpc
from opentelemetry import trace
from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter
from opentelemetry.instrumentation.grpc._aio_server import OpenTelemetryAioServerInterceptor
from opentelemetry.semconv.trace import SpanAttributes
from opentelemetry.sdk.resources import Resource
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import (
BatchSpanProcessor,
ConsoleSpanExporter,
SimpleSpanProcessor,
)
from typing import Optional
class OpenTelemetryAioServerInterceptorUnix(OpenTelemetryAioServerInterceptor):
def __init__(self):
super().__init__(trace.get_tracer(__name__))
def _start_span(
self, handler_call_details, context, set_status_on_exception=False
):
"""
Rewrite _start_span method to support Unix socket gRPC context
"""
# standard attributes
attributes = {
SpanAttributes.RPC_SYSTEM: "grpc",
SpanAttributes.RPC_GRPC_STATUS_CODE: grpc.StatusCode.OK.value[0],
}
# if we have details about the call, split into service and method
if handler_call_details.method:
service, method = handler_call_details.method.lstrip("/").split(
"/", 1
)
attributes.update(
{
SpanAttributes.RPC_METHOD: method,
SpanAttributes.RPC_SERVICE: service,
}
)
# add some attributes from the metadata
metadata = dict(context.invocation_metadata())
if "user-agent" in metadata:
attributes["rpc.user_agent"] = metadata["user-agent"]
# We use gRPC over a UNIX socket
attributes.update({SpanAttributes.NET_TRANSPORT: "unix"})
return self._tracer.start_as_current_span(
name=handler_call_details.method,
kind=trace.SpanKind.SERVER,
attributes=attributes,
set_status_on_exception=set_status_on_exception,
)
def setup_tracing(shard: int, otlp_endpoint: Optional[str]):
resource = Resource.create(attributes={"service.name": f"text-generation-server.{shard}"})
trace.set_tracer_provider(TracerProvider(resource=resource))
if otlp_endpoint is None:
# span_exporter = ConsoleSpanExporter(out=open(os.devnull, "w"))
span_exporter = ConsoleSpanExporter()
span_processor = SimpleSpanProcessor(span_exporter)
else:
span_exporter = OTLPSpanExporter(endpoint=otlp_endpoint, insecure=True)
span_processor = BatchSpanProcessor(span_exporter)
trace.get_tracer_provider().add_span_processor(span_processor)