[NVIDIA] [Perf] Update to leverage flashinfer trtllm FP4 MOE throughput kernel (#26714)

Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
jiahanc
2025-10-16 16:20:25 -07:00
committed by GitHub
co-authored by Michael Goin
parent fb5e10d3fb
commit 41d3071918
7 changed files with 25 additions and 96 deletions
+1 -1
View File
@@ -12,4 +12,4 @@ torchvision==0.23.0 # Required for phi3v processor. See https://github.com/pytor
# https://github.com/facebookresearch/xformers/releases/tag/v0.0.32.post1
xformers==0.0.32.post1; platform_system == 'Linux' and platform_machine == 'x86_64' # Requires PyTorch >= 2.8
# FlashInfer should be updated together with the Dockerfile
flashinfer-python==0.4.0
flashinfer-python==0.4.1