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

Evaluate Qwen30 prefill simulator fidelity

Browse Source
This commit is contained in:
Gahow Wang
2026-07-17 03:11:45 +08:00
parent 97c2f34700
commit 3a59d5df96
20 changed files with 8280 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
runs/frontier-phase-factorial-v0/jobs_base_rerun.toml Normal file
View File

@@ -0,0 +1,21 @@
version = 1
[[jobs]]
name = "qwen30-prefill-real-tp4-mns64-20260717-v2b-exclusive"
gpus = 4
gpu_model = "H20"
hosts = ["dash0"]
command = "cd /home/admin/cpfs/wjh/aituner/aituner-qwen30-vllm020-profile-v1/runs/frontier-phase-factorial-v0 && timeout --signal=TERM --kill-after=30s 7200 bash run_qwen30_prefill_real_config.sh"
artifacts = ["artifacts/real-tp4-mns64-v1"]
[jobs.env]
HOME = "/tmp/wjh"
XDG_CACHE_HOME = "/tmp/wjh/.cache"
VLLM_CACHE_ROOT = "/tmp/wjh/.cache/vllm"
TP = "4"
MNS = "64"
RATES = "4 8 16 32 64"
SERVER_PORT = "8731"
OUTPUT_ROOT = "/home/admin/cpfs/wjh/aituner/gpu-fleet-phase-factorial-v0/artifacts/real-tp4-mns64-v1"
VENV_ROOT = "/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1"
MODEL_ROOT = "/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B"