huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-22 15:32:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update to marlin-kernels 0.3.7 (#2882)

Browse Source 
This fixes a race condition. See:

https://github.com/vllm-project/vllm/pull/11493
This commit is contained in:
Daniël de Kok 2025-01-10 12:43:44 +01:00 committed by GitHub
parent da5ab46705
commit 4f7e00f4ce
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 22 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
flake.lock
View File

@ -978,16 +978,15 @@
"nixpkgs": "nixpkgs_6" "nixpkgs": "nixpkgs_6"
}, },
"locked": { "locked": {
"lastModified": 1736179589, "lastModified": 1736436388,
"narHash": "sha256-/zZCSieBJncVXqOFbvbSov76g2eWAxVxEJNNA6SmQKc=", "narHash": "sha256-CIyxVPpM9RrSwthNT/4DQ10YPk/uwzP7AeE83kBNsrE=",
"owner": "huggingface", "owner": "huggingface",
"repo": "text-generation-inference-nix", "repo": "text-generation-inference-nix",
"rev": "fc7ff53b2cd5c984ad1434f20c271e3b7600d1c4", "rev": "5103c3fb1f9ad1fd33b6e09ff05e957884b112d5",
"type": "github" "type": "github"
}, },
"original": { "original": {
"owner": "huggingface", "owner": "huggingface",
"ref": "flashinfer-v0.2",
"repo": "text-generation-inference-nix", "repo": "text-generation-inference-nix",
"type": "github" "type": "github"
} }

2
flake.nix
View File

@ -5,7 +5,7 @@
inputs.nixpkgs.follows = "tgi-nix/nixpkgs"; inputs.nixpkgs.follows = "tgi-nix/nixpkgs";
}; };
nix-filter.url = "github:numtide/nix-filter"; nix-filter.url = "github:numtide/nix-filter";
tgi-nix.url = "github:huggingface/text-generation-inference-nix/flashinfer-v0.2"; tgi-nix.url = "github:huggingface/text-generation-inference-nix";
nixpkgs.follows = "tgi-nix/nixpkgs"; nixpkgs.follows = "tgi-nix/nixpkgs";
flake-utils.url = "github:numtide/flake-utils"; flake-utils.url = "github:numtide/flake-utils";
rust-overlay = { rust-overlay = {

28
server/poetry.lock generated
View File

@ -1,4 +1,4 @@
# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand. # This file is automatically @generated by Poetry 1.8.5 and should not be changed by hand.
[[package]] [[package]]
name = "accelerate" name = "accelerate"
@ -1289,12 +1289,12 @@ files = [
[[package]] [[package]]
name = "marlin-kernels" name = "marlin-kernels"
version = "0.3.6" version = "0.3.7"
description = "Marlin quantization kernels" description = "Marlin quantization kernels"
optional = true optional = true
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "marlin_kernels-0.3.6+cu123torch2.4-cp310-cp310-linux_x86_64.whl", hash = "sha256:afedaa9a15e8991442bc8c81f62833fbf5c1556ae9d7a5a9e13b747ce97beef9"}, {file = "marlin_kernels-0.3.7+cu123torch2.4-cp310-cp310-linux_x86_64.whl", hash = "sha256:bb416d14623dc0ad0eeb2835446c37a41f994555f1baec8701de6d4c1fc17ec8"},
] ]
[package.dependencies] [package.dependencies]
@ -1302,16 +1302,16 @@ torch = "*"
[package.source] [package.source]
type = "url" type = "url"
url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.6/marlin_kernels-0.3.6+cu123torch2.4-cp310-cp310-linux_x86_64.whl" url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.4-cp310-cp310-linux_x86_64.whl"
[[package]] [[package]]
name = "marlin-kernels" name = "marlin-kernels"
version = "0.3.6" version = "0.3.7"
description = "Marlin quantization kernels" description = "Marlin quantization kernels"
optional = true optional = true
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "marlin_kernels-0.3.6+cu123torch2.4-cp311-cp311-linux_x86_64.whl", hash = "sha256:c0c05621d5e87144415d8a6e439072bd844d5f3cb55e4c4c69eabdc4c94610f4"}, {file = "marlin_kernels-0.3.7+cu123torch2.4-cp311-cp311-linux_x86_64.whl", hash = "sha256:a89bb61d718002d4432158641bce95c6fd68f9ee1a7d5402dd283903397f3185"},
] ]
[package.dependencies] [package.dependencies]
@ -1319,16 +1319,16 @@ torch = "*"
[package.source] [package.source]
type = "url" type = "url"
url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.6/marlin_kernels-0.3.6+cu123torch2.4-cp311-cp311-linux_x86_64.whl" url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.4-cp311-cp311-linux_x86_64.whl"
[[package]] [[package]]
name = "marlin-kernels" name = "marlin-kernels"
version = "0.3.6" version = "0.3.7"
description = "Marlin quantization kernels" description = "Marlin quantization kernels"
optional = true optional = true
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "marlin_kernels-0.3.6+cu123torch2.4-cp312-cp312-linux_x86_64.whl", hash = "sha256:3be4662c8d25a3cdb1793dafe0e2e76dd600913a69a468e2c68d1fed4e149255"}, {file = "marlin_kernels-0.3.7+cu123torch2.4-cp312-cp312-linux_x86_64.whl", hash = "sha256:ed938d196fc5e9cce9fc44cd2b889d5adc5ca7475c8a23858f1474d29e38bdbf"},
] ]
[package.dependencies] [package.dependencies]
@ -1336,16 +1336,16 @@ torch = "*"
[package.source] [package.source]
type = "url" type = "url"
url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.6/marlin_kernels-0.3.6+cu123torch2.4-cp312-cp312-linux_x86_64.whl" url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.4-cp312-cp312-linux_x86_64.whl"
[[package]] [[package]]
name = "marlin-kernels" name = "marlin-kernels"
version = "0.3.6" version = "0.3.7"
description = "Marlin quantization kernels" description = "Marlin quantization kernels"
optional = true optional = true
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "marlin_kernels-0.3.6+cu123torch2.4-cp39-cp39-linux_x86_64.whl", hash = "sha256:89eac9d46bc084a256b538afda6053683eb7e505db0e0d4f6dbeca32368caac6"}, {file = "marlin_kernels-0.3.7+cu123torch2.4-cp39-cp39-linux_x86_64.whl", hash = "sha256:113c54f68565ad476ca12366b4de92131fa3e9ddb16cbe8ad63272972a15ac28"},
] ]
[package.dependencies] [package.dependencies]
@ -1353,7 +1353,7 @@ torch = "*"
[package.source] [package.source]
type = "url" type = "url"
url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.6/marlin_kernels-0.3.6+cu123torch2.4-cp39-cp39-linux_x86_64.whl" url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.4-cp39-cp39-linux_x86_64.whl"
[[package]] [[package]]
name = "mdurl" name = "mdurl"
@ -4097,4 +4097,4 @@ torch = ["torch"]
[metadata] [metadata]
lock-version = "2.0" lock-version = "2.0"
python-versions = ">=3.9,<3.13" python-versions = ">=3.9,<3.13"
content-hash = "c7fdcff2b752cd3beb3995c1ecd15f0f4d9b4e117048b06ab991c6d0e0c86ff3" content-hash = "25f96d5dea777bfa7a959f863e35d2e05e1a6172d0dd45193dbe25ac2f32cc25"

8
server/pyproject.toml
View File

@ -48,10 +48,10 @@ attention-kernels = [
{ url = "https://github.com/danieldk/attention-kernels/releases/download/v0.1.1/attention_kernels-0.1.1+cu123torch2.4-cp312-cp312-linux_x86_64.whl", python = "~3.12", optional = true }, { url = "https://github.com/danieldk/attention-kernels/releases/download/v0.1.1/attention_kernels-0.1.1+cu123torch2.4-cp312-cp312-linux_x86_64.whl", python = "~3.12", optional = true },
] ]
marlin-kernels = [ marlin-kernels = [
{ url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.6/marlin_kernels-0.3.6+cu123torch2.4-cp39-cp39-linux_x86_64.whl", python = "~3.9", optional = true }, { url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.4-cp39-cp39-linux_x86_64.whl", python = "~3.9", optional = true },
{ url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.6/marlin_kernels-0.3.6+cu123torch2.4-cp310-cp310-linux_x86_64.whl", python = "~3.10", optional = true }, { url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.4-cp310-cp310-linux_x86_64.whl", python = "~3.10", optional = true },
{ url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.6/marlin_kernels-0.3.6+cu123torch2.4-cp311-cp311-linux_x86_64.whl", python = "~3.11", optional = true }, { url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.4-cp311-cp311-linux_x86_64.whl", python = "~3.11", optional = true },
{ url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.6/marlin_kernels-0.3.6+cu123torch2.4-cp312-cp312-linux_x86_64.whl", python = "~3.12", optional = true }, { url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.4-cp312-cp312-linux_x86_64.whl", python = "~3.12", optional = true },
] ]
moe-kernels = [ moe-kernels = [
{ url = "https://github.com/danieldk/moe-kernels/releases/download/v0.7.0/moe_kernels-0.7.0+cu123torch2.4-cp39-cp39-linux_x86_64.whl", python = "~3.9", optional = true }, { url = "https://github.com/danieldk/moe-kernels/releases/download/v0.7.0/moe_kernels-0.7.0+cu123torch2.4-cp39-cp39-linux_x86_64.whl", python = "~3.9", optional = true },