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

Add decode batch-grid stability experiment

Browse Source
This commit is contained in:
Gahow Wang
2026-07-23 16:55:55 +08:00
parent cb67ac8621
commit c1c200b7cd
11 changed files with 2498 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
runs/frontier-decode-batch-grid-v0/jobs-smoke-r1.toml Normal file
View File

@@ -0,0 +1,16 @@
version = 1
[[jobs]]
name = "decode-batch-tp4-b2-r1-20260723"
gpus = 4
gpu_model = "H20"
hosts = ["dash1"]
command = "timeout --signal=TERM --kill-after=60s 1800 bash runs/frontier-decode-batch-grid-v0/run_decode_profile.sh"
artifacts = ["runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b2-r1"]
[jobs.env]
TP = "4"
PROFILE_BATCH = "2"
SERVER_PORT = "9831"
OUTPUT_ROOT = "runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b2-r1"
FLASHINFER_WORKSPACE_BASE = "/tmp/frontier-component-flashinfer-v4"