Merge branch 'main' into flashinfer-gen

Dockerfile.mxfp4

@@ -98,7 +98,7 @@ ARG FLASHINFER_REPO=https://github.com/christopherowen/flashinfer.git
 ARG CUTLASS_REPO=https://github.com/christopherowen/cutlass.git
 
 ARG FLASHINFER_SHA=f349e52496a72a00d8c4ac02c7a1e38523ff7194
-ARG CUTLASS_SHA=11af7f02ab52c9130e422eeb4b44042fbd60c083
+ARG CUTLASS_SHA=7554e4a32b15929289aa80e8bc8a4e5f6f779407
 
 RUN --mount=type=cache,id=uv-cache,target=/root/.cache/uv \
      uv pip install nvidia-nvshmem-cu13 "apache-tvm-ffi<0.2"
@@ -167,7 +167,7 @@ ARG CACHEBUST_VLLM=1
 ARG VLLM_REPO=https://github.com/christopherowen/vllm.git
 
 # Git reference (branch, tag, or SHA) to checkout
-ARG VLLM_SHA=459541683f2d8c21f9c0e2f44954b04f59611cbe
+ARG VLLM_SHA=045293d82b832229560ac4a13152a095af603b6e
 
 # 4. Smart Git Clone (Fetch changes instead of full re-clone)
 # We mount a cache at /repo-cache. This directory persists on your host machine.

README.md

@@ -784,6 +784,7 @@ You can override the auto-detected values if needed:
 | `--eth-if` | Ethernet interface name. |
 | `--ib-if` | InfiniBand interface name. |
 | `-e, --env` | Environment variable to pass to container (e.g. `-e VAR=val`). Can be used multiple times. |
+| `-j` | Number of parallel jobs for build environment variables (optional). |
 | `--apply-mod` | Apply mods/patches from specified directory. Can be used multiple times to apply multiple mods. |
 | `--nccl-debug` | NCCL debug level (e.g., INFO, WARN). Defaults to INFO if flag is present but value is omitted. |
 | `--check-config` | Check configuration and auto-detection without launching. |