Add decode batch-grid stability experiment

This commit is contained in:
2026-07-23 16:55:55 +08:00
parent cb67ac8621
commit c1c200b7cd
11 changed files with 2498 additions and 0 deletions

View File

@@ -0,0 +1,46 @@
version = 1
[paths]
state_dir = "runs/frontier-decode-batch-grid-v0/fleet-state"
artifacts_dir = "runs/frontier-decode-batch-grid-v0/fleet-artifacts"
[ssh]
connect_timeout_sec = 10
[scheduler]
gpu_free_memory_mb = 1024
gpu_free_utilization_pct = 10
prefer_pack = true
# Code is synchronized by Git. The mandatory scp pass uses an empty directory.
[sync]
mode = "scp"
local_path = "/tmp/frontier-decode-batch-grid-v0-empty-sync"
[[hosts]]
name = "dash1"
ssh_alias = "dash1"
enabled = true
sync_remote_path = "/home/admin/cpfs/wjh/aituner/aituner-frontier-decode-batch-grid-v0"
fleet_root = "/home/admin/cpfs/wjh/aituner/gpu-fleet-decode-batch-grid-v0/dash1"
[[hosts]]
name = "dash2"
ssh_alias = "dash2"
enabled = true
sync_remote_path = "/home/admin/cpfs/wjh/aituner/aituner-frontier-decode-batch-grid-v0"
fleet_root = "/home/admin/cpfs/wjh/aituner/gpu-fleet-decode-batch-grid-v0/dash2"
[[hosts]]
name = "dash3"
ssh_alias = "dash3"
enabled = true
sync_remote_path = "/home/admin/cpfs/wjh/aituner/aituner-frontier-decode-batch-grid-v0"
fleet_root = "/home/admin/cpfs/wjh/aituner/gpu-fleet-decode-batch-grid-v0/dash3"
[[hosts]]
name = "dash4"
ssh_alias = "dash4"
enabled = true
sync_remote_path = "/home/admin/cpfs/wjh/aituner/aituner-frontier-decode-batch-grid-v0"
fleet_root = "/home/admin/cpfs/wjh/aituner/gpu-fleet-decode-batch-grid-v0/dash4"