mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-11 12:24:53 +00:00
Upgrading bitsandbytes.
Co-Authored-By: Matthew Douglas <38992547+matthewdouglas@users.noreply.github.com>
This commit is contained in:
parent
dc9b8e9814
commit
a70d2749f1
@ -2079,14 +2079,7 @@ 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![]
|
||||
}
|
||||
|
2261
server/poetry.lock
generated
2261
server/poetry.lock
generated
File diff suppressed because it is too large
Load Diff
@ -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"
|
||||
|
@ -1,21 +1,21 @@
|
||||
certifi==2024.8.30 ; python_version >= "3.9" and python_version < "3.13"
|
||||
charset-normalizer==3.4.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
click==8.1.7 ; python_version >= "3.9" and python_version < "3.13"
|
||||
certifi==2024.12.14 ; python_version >= "3.9" and python_version < "3.13"
|
||||
charset-normalizer==3.4.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
click==8.1.8 ; python_version >= "3.9" and python_version < "3.13"
|
||||
colorama==0.4.6 ; python_version >= "3.9" and python_version < "3.13" and (sys_platform == "win32" or platform_system == "Windows")
|
||||
deprecated==1.2.14 ; python_version >= "3.9" and python_version < "3.13"
|
||||
deprecated==1.2.15 ; python_version >= "3.9" and python_version < "3.13"
|
||||
einops==0.8.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
filelock==3.16.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
fsspec==2024.6.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
googleapis-common-protos==1.65.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
googleapis-common-protos==1.66.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpc-interceptor==0.15.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio-reflection==1.62.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio-status==1.62.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio==1.68.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
hf-transfer==0.1.8 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio==1.69.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
hf-transfer==0.1.9 ; python_version >= "3.9" and python_version < "3.13"
|
||||
huggingface-hub==0.23.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
idna==3.10 ; python_version >= "3.9" and python_version < "3.13"
|
||||
importlib-metadata==7.1.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
loguru==0.7.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
importlib-metadata==8.4.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
loguru==0.7.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
markdown-it-py==3.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
mdurl==0.1.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
@ -29,27 +29,27 @@ opentelemetry-instrumentation==0.48b0 ; python_version >= "3.9" and python_versi
|
||||
opentelemetry-proto==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-sdk==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-semantic-conventions==0.48b0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
packaging==24.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pillow==11.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
packaging==24.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pillow==11.1.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
prometheus-client==0.21.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
protobuf==4.25.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pygments==2.18.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pygments==2.19.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pyyaml==6.0.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
regex==2024.9.11 ; python_version >= "3.9" and python_version < "3.13"
|
||||
regex==2024.11.6 ; python_version >= "3.9" and python_version < "3.13"
|
||||
requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
rich==13.9.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
safetensors==0.4.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
scipy==1.13.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
sentencepiece==0.2.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
setuptools==75.2.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
setuptools==75.8.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
shellingham==1.5.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tokenizers==0.20.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tqdm==4.66.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tqdm==4.67.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
transformers==4.46.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
typer==0.12.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
typing-extensions==4.12.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
urllib3==2.2.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
win32-setctime==1.1.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
|
||||
wrapt==1.16.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
zipp==3.20.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
urllib3==2.3.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
win32-setctime==1.2.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
|
||||
wrapt==1.17.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
zipp==3.21.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
|
@ -1,21 +1,21 @@
|
||||
certifi==2024.8.30 ; python_version >= "3.9" and python_version < "3.13"
|
||||
charset-normalizer==3.4.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
click==8.1.7 ; python_version >= "3.9" and python_version < "3.13"
|
||||
certifi==2024.12.14 ; python_version >= "3.9" and python_version < "3.13"
|
||||
charset-normalizer==3.4.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
click==8.1.8 ; python_version >= "3.9" and python_version < "3.13"
|
||||
colorama==0.4.6 ; python_version >= "3.9" and python_version < "3.13" and (sys_platform == "win32" or platform_system == "Windows")
|
||||
deprecated==1.2.14 ; python_version >= "3.9" and python_version < "3.13"
|
||||
deprecated==1.2.15 ; python_version >= "3.9" and python_version < "3.13"
|
||||
einops==0.8.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
filelock==3.16.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
fsspec==2024.6.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
googleapis-common-protos==1.65.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
googleapis-common-protos==1.66.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpc-interceptor==0.15.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio-reflection==1.62.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio-status==1.62.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio==1.68.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
hf-transfer==0.1.8 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio==1.69.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
hf-transfer==0.1.9 ; python_version >= "3.9" and python_version < "3.13"
|
||||
huggingface-hub==0.23.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
idna==3.10 ; python_version >= "3.9" and python_version < "3.13"
|
||||
importlib-metadata==7.1.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
loguru==0.7.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
importlib-metadata==8.4.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
loguru==0.7.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
markdown-it-py==3.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
mdurl==0.1.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
@ -29,27 +29,27 @@ opentelemetry-instrumentation==0.48b0 ; python_version >= "3.9" and python_versi
|
||||
opentelemetry-proto==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-sdk==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-semantic-conventions==0.48b0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
packaging==24.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pillow==11.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
packaging==24.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pillow==11.1.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
prometheus-client==0.21.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
protobuf==4.25.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pygments==2.18.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pygments==2.19.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pyyaml==6.0.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
regex==2024.9.11 ; python_version >= "3.9" and python_version < "3.13"
|
||||
regex==2024.11.6 ; python_version >= "3.9" and python_version < "3.13"
|
||||
requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
rich==13.9.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
safetensors==0.4.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
scipy==1.13.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
sentencepiece==0.2.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
setuptools==75.2.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
setuptools==75.8.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
shellingham==1.5.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tokenizers==0.20.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tqdm==4.66.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tqdm==4.67.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
transformers==4.46.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
typer==0.12.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
typing-extensions==4.12.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
urllib3==2.2.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
win32-setctime==1.1.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
|
||||
wrapt==1.16.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
zipp==3.20.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
urllib3==2.3.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
win32-setctime==1.2.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
|
||||
wrapt==1.17.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
zipp==3.21.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
|
@ -1,21 +1,21 @@
|
||||
certifi==2024.8.30 ; python_version >= "3.9" and python_version < "3.13"
|
||||
charset-normalizer==3.4.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
click==8.1.7 ; python_version >= "3.9" and python_version < "3.13"
|
||||
certifi==2024.12.14 ; python_version >= "3.9" and python_version < "3.13"
|
||||
charset-normalizer==3.4.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
click==8.1.8 ; python_version >= "3.9" and python_version < "3.13"
|
||||
colorama==0.4.6 ; python_version >= "3.9" and python_version < "3.13" and (sys_platform == "win32" or platform_system == "Windows")
|
||||
deprecated==1.2.14 ; python_version >= "3.9" and python_version < "3.13"
|
||||
deprecated==1.2.15 ; python_version >= "3.9" and python_version < "3.13"
|
||||
einops==0.8.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
filelock==3.16.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
fsspec==2024.6.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
googleapis-common-protos==1.65.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
googleapis-common-protos==1.66.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpc-interceptor==0.15.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio-reflection==1.62.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio-status==1.62.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio==1.68.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
hf-transfer==0.1.8 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio==1.69.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
hf-transfer==0.1.9 ; python_version >= "3.9" and python_version < "3.13"
|
||||
huggingface-hub==0.23.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
idna==3.10 ; python_version >= "3.9" and python_version < "3.13"
|
||||
importlib-metadata==7.1.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
loguru==0.7.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
importlib-metadata==8.4.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
loguru==0.7.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
markdown-it-py==3.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
mdurl==0.1.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
@ -29,27 +29,27 @@ opentelemetry-instrumentation==0.48b0 ; python_version >= "3.9" and python_versi
|
||||
opentelemetry-proto==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-sdk==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-semantic-conventions==0.48b0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
packaging==24.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pillow==11.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
packaging==24.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pillow==11.1.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
prometheus-client==0.21.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
protobuf==4.25.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pygments==2.18.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pygments==2.19.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pyyaml==6.0.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
regex==2024.9.11 ; python_version >= "3.9" and python_version < "3.13"
|
||||
regex==2024.11.6 ; python_version >= "3.9" and python_version < "3.13"
|
||||
requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
rich==13.9.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
safetensors==0.4.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
scipy==1.13.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
sentencepiece==0.2.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
setuptools==75.2.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
setuptools==75.8.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
shellingham==1.5.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tokenizers==0.20.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tqdm==4.66.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tqdm==4.67.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
transformers==4.46.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
typer==0.12.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
typing-extensions==4.12.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
urllib3==2.2.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
win32-setctime==1.1.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
|
||||
wrapt==1.16.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
zipp==3.20.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
urllib3==2.3.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
win32-setctime==1.2.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
|
||||
wrapt==1.17.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
zipp==3.21.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
|
Loading…
Reference in New Issue
Block a user