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

Keep Qwen30 JIT cache scoped to experiment

Browse Source
This commit is contained in:
Gahow Wang
2026-07-18 11:11:10 +08:00
parent ecb45cf762
commit b7f9cef9c5
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
runs/frontier-fidelity-envelope-v1/run_qwen30_latency_case_real_surface.sh
View File

@@ -16,7 +16,7 @@ CLIENT="${RUNNER_DIR}/qwen30_exact_trace_client.py"
PREFILL_CLIENT="${RUNNER_DIR}/../frontier-phase-factorial-v0/qwen30_prefill_client.py" PREFILL_CLIENT="${RUNNER_DIR}/../frontier-phase-factorial-v0/qwen30_prefill_client.py"
VENV_ROOT="${VENV_ROOT:-/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1}" VENV_ROOT="${VENV_ROOT:-/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1}"
MODEL_ROOT="${MODEL_ROOT:-/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B}" MODEL_ROOT="${MODEL_ROOT:-/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B}"
FLASHINFER_SHARED_WORKSPACE="${FLASHINFER_SHARED_WORKSPACE:-/tmp/wjh/flashinfer-workspace-vllm020-profiler-v1}" FLASHINFER_SHARED_WORKSPACE="${FLASHINFER_SHARED_WORKSPACE:-${OUT}/flashinfer-shared-workspace}"
SERVER_READY_ATTEMPTS="${SERVER_READY_ATTEMPTS:-300}" SERVER_READY_ATTEMPTS="${SERVER_READY_ATTEMPTS:-300}"
PORT="${BASE_PORT:-8300}" PORT="${BASE_PORT:-8300}"