gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Set Qwen3 model type for vLLM profile dispatch

Browse Source
This commit is contained in:
Gahow Wang
2026-07-19 06:12:11 +08:00
parent a21382c8aa
commit d563c30b42
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
runs/frontier-fidelity-envelope-v1/run_q235_after_q30.sh
View File

@@ -13,6 +13,7 @@ VENV_ROOT="${VENV_ROOT:-/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1}"
# FlashInfer's TensorRT-LLM MoE runtime invokes `nvcc` by name when it # FlashInfer's TensorRT-LLM MoE runtime invokes `nvcc` by name when it
# autotunes a previously unseen FP8 grouped-GEMM shape. # autotunes a previously unseen FP8 grouped-GEMM shape.
export PATH="/usr/local/cuda/bin:${PATH}" export PATH="/usr/local/cuda/bin:${PATH}"
export FRONTIER_VLLM_MODEL_TYPE=qwen3_moe
command -v nvcc >/dev/null command -v nvcc >/dev/null
mkdir -p "${OUTPUT_ROOT}/supervisor" "${PROFILE_ROOT}" mkdir -p "${OUTPUT_ROOT}/supervisor" "${PROFILE_ROOT}"