Set Qwen3 model type for vLLM profile dispatch
This commit is contained in:
@@ -13,6 +13,7 @@ VENV_ROOT="${VENV_ROOT:-/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1}"
|
||||
# FlashInfer's TensorRT-LLM MoE runtime invokes `nvcc` by name when it
|
||||
# autotunes a previously unseen FP8 grouped-GEMM shape.
|
||||
export PATH="/usr/local/cuda/bin:${PATH}"
|
||||
export FRONTIER_VLLM_MODEL_TYPE=qwen3_moe
|
||||
command -v nvcc >/dev/null
|
||||
|
||||
mkdir -p "${OUTPUT_ROOT}/supervisor" "${PROFILE_ROOT}"
|
||||
|
||||
Reference in New Issue
Block a user