[Misc] Upgrade fastsafetensors version, fix metadata is null (#50827)
Signed-off-by: lengrongfu <lenronfu@gmail.com> Signed-off-by: Nick Hill <nickhill123@gmail.com> Co-authored-by: Nick Hill <nickhill123@gmail.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
Nick Hill
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
c5d470ac4c
commit
a07086e403
@@ -22,7 +22,7 @@ nvidia-cudnn-frontend>=1.19.1
|
|||||||
# Required for LLM_NVTX_SCOPES_FOR_PROFILING=1
|
# Required for LLM_NVTX_SCOPES_FOR_PROFILING=1
|
||||||
nvtx==0.2.15
|
nvtx==0.2.15
|
||||||
# Required for faster safetensors model loading
|
# Required for faster safetensors model loading
|
||||||
fastsafetensors >= 0.3.2
|
fastsafetensors >= 0.3.3
|
||||||
|
|
||||||
# QuACK and Cutlass DSL for FA4 (cute-DSL implementation)
|
# QuACK and Cutlass DSL for FA4 (cute-DSL implementation)
|
||||||
nvidia-cutlass-dsl[cu13]==4.6.0
|
nvidia-cutlass-dsl[cu13]==4.6.0
|
||||||
|
|||||||
@@ -26,4 +26,4 @@ tilelang==0.1.10
|
|||||||
# Required apache-tvm-ffi matching tilelang version
|
# Required apache-tvm-ffi matching tilelang version
|
||||||
apache-tvm-ffi==0.1.10
|
apache-tvm-ffi==0.1.10
|
||||||
# Required for faster safetensors model loading
|
# Required for faster safetensors model loading
|
||||||
fastsafetensors >= 0.3.2
|
fastsafetensors >= 0.3.3
|
||||||
|
|||||||
@@ -234,7 +234,7 @@ fastparquet==2024.11.0
|
|||||||
# via genai-perf
|
# via genai-perf
|
||||||
fastrlock==0.8.2
|
fastrlock==0.8.2
|
||||||
# via cupy-cuda12x
|
# via cupy-cuda12x
|
||||||
fastsafetensors==0.3.2
|
fastsafetensors==0.3.3
|
||||||
# via -r requirements/test/cuda.in
|
# via -r requirements/test/cuda.in
|
||||||
filelock==3.16.1
|
filelock==3.16.1
|
||||||
# via
|
# via
|
||||||
|
|||||||
@@ -57,7 +57,7 @@ grpcio-reflection==1.78.0
|
|||||||
arctic-inference == 0.1.1; platform_machine == "x86_64" # Required for suffix decoding test
|
arctic-inference == 0.1.1; platform_machine == "x86_64" # Required for suffix decoding test
|
||||||
numba == 0.65.0 # Required for N-gram speculative decoding
|
numba == 0.65.0 # Required for N-gram speculative decoding
|
||||||
runai-model-streamer[s3,gcs,azure]==0.15.7
|
runai-model-streamer[s3,gcs,azure]==0.15.7
|
||||||
fastsafetensors>=0.3.2
|
fastsafetensors>=0.3.3
|
||||||
instanttensor>=0.1.9; platform_machine == "x86_64"
|
instanttensor>=0.1.9; platform_machine == "x86_64"
|
||||||
decord==0.6.0; platform_machine == "x86_64"
|
decord==0.6.0; platform_machine == "x86_64"
|
||||||
# terratorch is temporarily disabled while PyPI has the `lightning` package
|
# terratorch is temporarily disabled while PyPI has the `lightning` package
|
||||||
|
|||||||
@@ -250,7 +250,7 @@ fastparquet==2024.11.0
|
|||||||
# via genai-perf
|
# via genai-perf
|
||||||
fastrlock==0.8.2
|
fastrlock==0.8.2
|
||||||
# via cupy-cuda12x
|
# via cupy-cuda12x
|
||||||
fastsafetensors==0.3.2
|
fastsafetensors==0.3.3
|
||||||
# via
|
# via
|
||||||
# -c requirements/cuda.txt
|
# -c requirements/cuda.txt
|
||||||
# -r requirements/test/cuda.in
|
# -r requirements/test/cuda.in
|
||||||
|
|||||||
@@ -43,6 +43,6 @@ tritonclient>=2.51.0
|
|||||||
numba == 0.65.0 # Required for N-gram speculative decoding
|
numba == 0.65.0 # Required for N-gram speculative decoding
|
||||||
numpy
|
numpy
|
||||||
runai-model-streamer[s3,gcs,azure]==0.15.7
|
runai-model-streamer[s3,gcs,azure]==0.15.7
|
||||||
fastsafetensors>=0.3.2
|
fastsafetensors>=0.3.3
|
||||||
instanttensor>=0.1.9
|
instanttensor>=0.1.9
|
||||||
pydantic>=2.12 # 2.11 leads to error on python 3.13
|
pydantic>=2.12 # 2.11 leads to error on python 3.13
|
||||||
|
|||||||
@@ -53,7 +53,7 @@ grpcio-reflection==1.78.0
|
|||||||
arctic-inference==0.1.1 # Required for suffix decoding test
|
arctic-inference==0.1.1 # Required for suffix decoding test
|
||||||
numba==0.65.0 # Required for N-gram speculative decoding
|
numba==0.65.0 # Required for N-gram speculative decoding
|
||||||
runai-model-streamer[s3,gcs,azure]==0.15.7
|
runai-model-streamer[s3,gcs,azure]==0.15.7
|
||||||
fastsafetensors>=0.3.2
|
fastsafetensors>=0.3.3
|
||||||
instanttensor>=0.1.9
|
instanttensor>=0.1.9
|
||||||
decord==0.6.0
|
decord==0.6.0
|
||||||
|
|
||||||
|
|||||||
@@ -237,7 +237,7 @@ fastavro==1.12.2
|
|||||||
# via cohere
|
# via cohere
|
||||||
fastparquet==2026.3.0
|
fastparquet==2026.3.0
|
||||||
# via genai-perf
|
# via genai-perf
|
||||||
fastsafetensors==0.3.2
|
fastsafetensors==0.3.3
|
||||||
# via
|
# via
|
||||||
# -c requirements/rocm.txt
|
# -c requirements/rocm.txt
|
||||||
# -r requirements/test/rocm.in
|
# -r requirements/test/rocm.in
|
||||||
|
|||||||
@@ -1272,7 +1272,7 @@ setup(
|
|||||||
"zen": ["zentorch==2.11.0.0"],
|
"zen": ["zentorch==2.11.0.0"],
|
||||||
"bench": ["pandas", "matplotlib", "seaborn", "datasets", "scipy", "plotly"],
|
"bench": ["pandas", "matplotlib", "seaborn", "datasets", "scipy", "plotly"],
|
||||||
"tensorizer": ["tensorizer==2.10.1"],
|
"tensorizer": ["tensorizer==2.10.1"],
|
||||||
"fastsafetensors": ["fastsafetensors >= 0.3.2"],
|
"fastsafetensors": ["fastsafetensors >= 0.3.3"],
|
||||||
"instanttensor": ["instanttensor >= 0.1.9"],
|
"instanttensor": ["instanttensor >= 0.1.9"],
|
||||||
"runai": ["runai-model-streamer[s3,gcs,azure] >= 0.15.7"],
|
"runai": ["runai-model-streamer[s3,gcs,azure] >= 0.15.7"],
|
||||||
"audio": [
|
"audio": [
|
||||||
|
|||||||
Reference in New Issue
Block a user