fix nccl issue

This commit is contained in:
fxmarty 2024-06-20 17:57:45 +00:00
parent bcb3faa1c2
commit 2502ce4865
4 changed files with 44 additions and 37 deletions

View File

@ -34,5 +34,5 @@ run-dev:
SAFETENSORS_FAST_GPU=1 python -m torch.distributed.run --nproc_per_node=2 text_generation_server/cli.py serve bigscience/bloom-560m --sharded
export-requirements:
poetry export -o requirements_cuda.txt --without-hashes
poetry export -o requirements_cuda.txt --without-hashes --with cuda
poetry export -o requirements_rocm.txt --without-hashes

View File

@ -50,6 +50,9 @@ outlines = ["outlines"]
grpcio-tools = "^1.51.1"
pytest = "^7.3.0"
[tool.poetry.group.cuda.dependencies]
# Fix https://github.com/NVIDIA/nccl/issues/1251 bug in nccl 2.20.5 bundled with PyTorch 2.3, nccl 2.21 appears to fix the issue.
nvidia-nccl-cu12 = "==2.21.5"
[[tool.poetry.source]]
name = "pytorch-gpu-src"

View File

@ -1,31 +1,32 @@
backoff==2.2.1 ; python_version >= "3.9" and python_version < "3.13"
certifi==2024.2.2 ; python_version >= "3.9" and python_version < "3.13"
certifi==2024.6.2 ; python_version >= "3.9" and python_version < "3.13"
charset-normalizer==3.3.2 ; python_version >= "3.9" and python_version < "3.13"
click==8.1.7 ; 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"
einops==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
filelock==3.14.0 ; python_version >= "3.9" and python_version < "3.13"
fsspec==2024.5.0 ; python_version >= "3.9" and python_version < "3.13"
googleapis-common-protos==1.63.0 ; python_version >= "3.9" and python_version < "3.13"
fsspec==2024.6.0 ; python_version >= "3.9" and python_version < "3.13"
googleapis-common-protos==1.63.1 ; 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==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
grpcio-status==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
grpcio==1.64.0 ; python_version >= "3.9" and python_version < "3.13"
grpcio==1.64.1 ; python_version >= "3.9" and python_version < "3.13"
hf-transfer==0.1.6 ; python_version >= "3.9" and python_version < "3.13"
huggingface-hub==0.23.1 ; python_version >= "3.9" and python_version < "3.13"
huggingface-hub==0.23.2 ; python_version >= "3.9" and python_version < "3.13"
idna==3.7 ; python_version >= "3.9" and python_version < "3.13"
importlib-metadata==7.1.0 ; python_version >= "3.9" and python_version < "3.13"
loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13"
numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-api==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp-proto-grpc==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp-proto-http==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-instrumentation-grpc==0.36b0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-instrumentation==0.36b0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-proto==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-sdk==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-semantic-conventions==0.36b0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-api==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp-proto-common==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp-proto-grpc==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp-proto-http==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-instrumentation-grpc==0.46b0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-instrumentation==0.46b0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-proto==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-sdk==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-semantic-conventions==0.46b0 ; python_version >= "3.9" and python_version < "3.13"
packaging==24.0 ; python_version >= "3.9" and python_version < "3.13"
pillow==10.3.0 ; python_version >= "3.9" and python_version < "3.13"
prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13"
@ -33,16 +34,17 @@ protobuf==4.25.3 ; python_version >= "3.9" and python_version < "3.13"
py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13"
pyyaml==6.0.1 ; python_version >= "3.9" and python_version < "3.13"
regex==2024.5.15 ; python_version >= "3.9" and python_version < "3.13"
requests==2.32.2 ; python_version >= "3.9" and python_version < "3.13"
requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13"
safetensors==0.4.3 ; python_version >= "3.9" and python_version < "3.13"
scipy==1.13.1 ; python_version >= "3.9" and python_version < "3.13"
sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13"
setuptools==70.0.0 ; python_version >= "3.9" and python_version < "3.13"
tokenizers==0.19.1 ; python_version >= "3.9" and python_version < "3.13"
tqdm==4.66.4 ; python_version >= "3.9" and python_version < "3.13"
transformers==4.41.1 ; python_version >= "3.9" and python_version < "3.13"
transformers==4.41.2 ; python_version >= "3.9" and python_version < "3.13"
typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
typing-extensions==4.12.0 ; python_version >= "3.9" and python_version < "3.13"
typing-extensions==4.12.1 ; python_version >= "3.9" and python_version < "3.13"
urllib3==2.2.1 ; 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==3.19.1 ; python_version >= "3.9" and python_version < "3.13"

View File

@ -1,31 +1,32 @@
backoff==2.2.1 ; python_version >= "3.9" and python_version < "3.13"
certifi==2024.2.2 ; python_version >= "3.9" and python_version < "3.13"
certifi==2024.6.2 ; python_version >= "3.9" and python_version < "3.13"
charset-normalizer==3.3.2 ; python_version >= "3.9" and python_version < "3.13"
click==8.1.7 ; 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"
einops==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
filelock==3.14.0 ; python_version >= "3.9" and python_version < "3.13"
fsspec==2024.5.0 ; python_version >= "3.9" and python_version < "3.13"
googleapis-common-protos==1.63.0 ; python_version >= "3.9" and python_version < "3.13"
fsspec==2024.6.0 ; python_version >= "3.9" and python_version < "3.13"
googleapis-common-protos==1.63.1 ; 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==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
grpcio-status==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
grpcio==1.64.0 ; python_version >= "3.9" and python_version < "3.13"
grpcio==1.64.1 ; python_version >= "3.9" and python_version < "3.13"
hf-transfer==0.1.6 ; python_version >= "3.9" and python_version < "3.13"
huggingface-hub==0.23.1 ; python_version >= "3.9" and python_version < "3.13"
huggingface-hub==0.23.2 ; python_version >= "3.9" and python_version < "3.13"
idna==3.7 ; python_version >= "3.9" and python_version < "3.13"
importlib-metadata==7.1.0 ; python_version >= "3.9" and python_version < "3.13"
loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13"
numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-api==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp-proto-grpc==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp-proto-http==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-instrumentation-grpc==0.36b0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-instrumentation==0.36b0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-proto==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-sdk==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-semantic-conventions==0.36b0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-api==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp-proto-common==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp-proto-grpc==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp-proto-http==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-exporter-otlp==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-instrumentation-grpc==0.46b0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-instrumentation==0.46b0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-proto==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-sdk==1.25.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-semantic-conventions==0.46b0 ; python_version >= "3.9" and python_version < "3.13"
packaging==24.0 ; python_version >= "3.9" and python_version < "3.13"
pillow==10.3.0 ; python_version >= "3.9" and python_version < "3.13"
prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13"
@ -33,16 +34,17 @@ protobuf==4.25.3 ; python_version >= "3.9" and python_version < "3.13"
py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13"
pyyaml==6.0.1 ; python_version >= "3.9" and python_version < "3.13"
regex==2024.5.15 ; python_version >= "3.9" and python_version < "3.13"
requests==2.32.2 ; python_version >= "3.9" and python_version < "3.13"
requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13"
safetensors==0.4.3 ; python_version >= "3.9" and python_version < "3.13"
scipy==1.13.1 ; python_version >= "3.9" and python_version < "3.13"
sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13"
setuptools==70.0.0 ; python_version >= "3.9" and python_version < "3.13"
tokenizers==0.19.1 ; python_version >= "3.9" and python_version < "3.13"
tqdm==4.66.4 ; python_version >= "3.9" and python_version < "3.13"
transformers==4.41.1 ; python_version >= "3.9" and python_version < "3.13"
transformers==4.41.2 ; python_version >= "3.9" and python_version < "3.13"
typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
typing-extensions==4.12.0 ; python_version >= "3.9" and python_version < "3.13"
typing-extensions==4.12.1 ; python_version >= "3.9" and python_version < "3.13"
urllib3==2.2.1 ; 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==3.19.1 ; python_version >= "3.9" and python_version < "3.13"