Update comment and ref for vllm

Author: krishung5

container/Dockerfile.vllm

@@ -16,10 +16,8 @@ ARG RUNTIME_IMAGE_TAG="12.8.1-runtime-ubuntu24.04"
 ARG VLLM_REF="77a6bf07aedf132aad2b6719f6d87abc5d3311ab"
 ARG TORCH_BACKEND="cu128"
 
-# Match 0.10.0 vLLM release
-# https://github.com/vllm-project/vllm/releases/tag/v0.10.0
-# Pinned to commit before https://github.com/deepseek-ai/DeepGEMM/pull/112 for DeepGEMM which seems to break on H100:
-# "RuntimeError: Failed: CUDA runtime error csrc/jit/kernel_runtime.hpp:108 '98'"
+# Match 0.10.1 vLLM release
+# https://github.com/vllm-project/vllm/releases/tag/v0.10.1
 ARG DEEPGEMM_REF="f85ec64"
 ARG FLASHINF_REF="v0.2.8rc1"
 

container/deps/vllm/install_vllm.sh

@@ -175,8 +175,6 @@ git checkout $DEEPGEMM_REF # Pin Version
 sed -i 's|[email protected]:|https://github.com/|g' .gitmodules
 git submodule sync --recursive
 git submodule update --init --recursive
-
-# command for 03d0be3
 python setup.py install
 
 # new install command for post 03d0be3

pyproject.toml

@@ -56,7 +56,7 @@ trtllm =[
 vllm = [
     "uvloop",
     "nixl<=0.4.1",
-    "vllm==0.10.0",
+    { git = "https://github.com/vllm-project/vllm.git", rev = "77a6bf07aedf132aad2b6719f6d87abc5d3311ab" },
 ]
 
 sglang = [