[Docker] Add fastsafetensors to NVIDIA Dockerfile (#38950)

This commit is contained in:
Zhewen Li
2026-04-08 22:21:37 -07:00
committed by GitHub
parent e80e633927
commit 9e78555743
5 changed files with 14 additions and 4 deletions
+3
View File
@@ -15,6 +15,9 @@ flashinfer-cubin==0.6.7
# breaking changes in 1.19.0
nvidia-cudnn-frontend>=1.13.0,<1.19.0
# Required for faster safetensors model loading
fastsafetensors >= 0.2.2
# QuACK and Cutlass DSL for FA4 (cute-DSL implementation)
nvidia-cutlass-dsl>=4.4.2
quack-kernels>=0.3.3
+3 -1
View File
@@ -276,7 +276,9 @@ fastar==0.9.0
fastparquet==2026.3.0
# via genai-perf
fastsafetensors==0.2.2
# via -r requirements/rocm-test.in
# via
# -c requirements/rocm.txt
# -r requirements/rocm-test.in
filelock==3.25.2
# via
# -c requirements/common.txt
+3 -1
View File
@@ -20,4 +20,6 @@ conch-triton-kernels==1.2.1
timm>=1.0.17
# amd-quark: required for Quark quantization on ROCm
# To be consistent with test_quark.py
amd-quark>=0.8.99
amd-quark>=0.8.99
# Required for faster safetensors model loading
fastsafetensors >= 0.2.2