huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-19 13:52:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Upgrading bitsandbytes. (#2910)

Browse Source 
* Upgrading bitsandbytes.

Co-Authored-By: Matthew Douglas <38992547+matthewdouglas@users.noreply.github.com>

* Tighter lock.

---------

Co-authored-by: Matthew Douglas <38992547+matthewdouglas@users.noreply.github.com>
This commit is contained in:
Nicolas Patry 2025-01-15 20:07:21 +01:00 committed by GitHub
parent 120bd3e3bb
commit 922cc38fbc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 9 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
launcher/src/main.rs
View File

@ -2078,14 +2078,7 @@ fn main() -> Result<(), LauncherError> {
let cuda_graphs = match (&args.cuda_graphs, &quantize) {
(Some(cuda_graphs), _) => cuda_graphs.iter().cloned().filter(|&c| c > 0).collect(),
#[allow(deprecated)]
(
None,
Some(
Quantization::Bitsandbytes
| Quantization::BitsandbytesNf4
| Quantization::BitsandbytesFp4,
),
) => {
(None, Some(Quantization::Bitsandbytes)) => {
tracing::warn!("Bitsandbytes doesn't work with cuda graphs, deactivating them");
vec![]
}

13
server/poetry.lock generated
View File

@ -1,4 +1,4 @@
# This file is automatically @generated by Poetry 1.8.5 and should not be changed by hand.
# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand.
[[package]]
name = "accelerate"
@ -290,22 +290,23 @@ tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"]
[[package]]
name = "bitsandbytes"
version = "0.43.3"
version = "0.45.0"
description = "k-bit optimizers and matrix multiplication routines."
optional = true
python-versions = "*"
files = [
{file = "bitsandbytes-0.43.3-py3-none-manylinux_2_24_x86_64.whl", hash = "sha256:cc99507c352be0715098b2c7577b690dd158972dc4ea10c7495bac104c7c79f0"},
{file = "bitsandbytes-0.43.3-py3-none-win_amd64.whl", hash = "sha256:257f6552f2144748a84e6c44e1f7a98f3da888f675ed74e18fd7f7eb13c6cafa"},
{file = "bitsandbytes-0.45.0-py3-none-manylinux_2_24_x86_64.whl", hash = "sha256:0f0323de1ff1fdf8383e79bdad1283516a4c05a6fd2b44a363bf4e059422305b"},
{file = "bitsandbytes-0.45.0-py3-none-win_amd64.whl", hash = "sha256:ebbf96e0ecb466716a65ecdeaef3fa1983575447b9ab66b74e5211892507c6ff"},
]
[package.dependencies]
numpy = "*"
torch = "*"
typing_extensions = ">=4.8.0"
[package.extras]
benchmark = ["matplotlib", "pandas"]
test = ["scipy"]
test = ["lion_pytorch", "scipy"]
[[package]]
name = "certifi"
@ -4097,4 +4098,4 @@ torch = ["torch"]
[metadata]
lock-version = "2.0"
python-versions = ">=3.9,<3.13"
content-hash = "25f96d5dea777bfa7a959f863e35d2e05e1a6172d0dd45193dbe25ac2f32cc25"
content-hash = "0ead8472620eeef6f9ff81f70bcb48403f9c831b6914245efa5e249724d80d0b"

2
server/pyproject.toml
View File

@ -16,7 +16,7 @@ grpcio-reflection = "^1.51.1"
grpc-interceptor = "^0.15.4"
typer = "^0.12.5"
accelerate = {version = "^1.1.0", optional = true}
bitsandbytes = { version = "^0.43.0", optional = true }
bitsandbytes = { version = "^0.45.0", optional = true }
safetensors = "^0.4.5"
loguru = "^0.7.2"
opentelemetry-api = "^1.27.0"