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

24
runs/frontier-qwen30-vllm020-profile-v1/fleet.toml Normal file
View File

@@ -0,0 +1,24 @@
version = 1
[paths]
state_dir = "runs/frontier-qwen30-vllm020-profile-v1/fleet-state"
artifacts_dir = "runs/frontier-qwen30-vllm020-profile-v1/fleet-artifacts"
[ssh]
connect_timeout_sec = 10
[scheduler]
gpu_free_memory_mb = 1024
gpu_free_utilization_pct = 10
prefer_pack = true
[sync]
mode = "scp"
local_path = "runs/frontier-qwen30-vllm020-profile-v1"
[[hosts]]
name = "dash0"
ssh_alias = "dash0"
enabled = true
sync_remote_path = "/home/admin/cpfs/wjh/aituner/aituner-qwen30-vllm020-profile-fleet"
fleet_root = "/home/admin/cpfs/wjh/aituner/gpu-fleet-qwen30-vllm020-profile-v1"