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

Add vLLM 0.20 per-TP FlashAttention profile smoke

Browse Source
This commit is contained in:
Gahow Wang
2026-07-16 21:00:27 +08:00
parent 13f0713bf2
commit e9a4be6153
7 changed files with 371 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
runs/frontier-qwen30-vllm020-profile-v1/jobs_smoke.toml Normal file
View File

@@ -0,0 +1,15 @@
version = 1
[[jobs]]
name = "qwen30-vllm020-flashattn-smoke-20260716-v1"
gpus = 1
gpu_model = "H20"
hosts = ["dash0"]
command = "cd /home/admin/cpfs/wjh/aituner/aituner-qwen30-vllm020-profile-v1/runs/frontier-qwen30-vllm020-profile-v1 && timeout --signal=TERM --kill-after=30s 900 bash run_flashattn_smoke.sh"
artifacts = ["artifacts/flashattn-smoke"]
[jobs.env]
OUTPUT_ROOT = "/home/admin/cpfs/wjh/aituner/aituner-qwen30-vllm020-profile-fleet/artifacts/flashattn-smoke"
VENV_ROOT = "/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1"
VLLM_SOURCE = "/home/admin/cpfs/wjh/agentic-kv/third_party/vllm_v20_build"
MODEL = "/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B"