Pass TP4 decode stability gate

This commit is contained in:
2026-07-23 17:09:49 +08:00
parent c1c200b7cd
commit 1126d9be7d
8 changed files with 1002 additions and 2 deletions

View File

@@ -0,0 +1,61 @@
version = 1
[[jobs]]
name = "decode-grid-tp2-b2-r2-20260723"
gpus = 2
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/tp2-b2-r2"]
[jobs.env]
TP = "2"
PROFILE_BATCH = "2"
SERVER_PORT = "9841"
OUTPUT_ROOT = "runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b2-r2"
FLASHINFER_WORKSPACE_BASE = "/tmp/frontier-component-flashinfer-v4"
[[jobs]]
name = "decode-grid-tp2-b4-r2-20260723"
gpus = 2
gpu_model = "H20"
hosts = ["dash2"]
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/tp2-b4-r2"]
[jobs.env]
TP = "2"
PROFILE_BATCH = "4"
SERVER_PORT = "9842"
OUTPUT_ROOT = "runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b4-r2"
FLASHINFER_WORKSPACE_BASE = "/tmp/frontier-component-flashinfer-v4"
[[jobs]]
name = "decode-grid-tp4-b4-r2-20260723"
gpus = 4
gpu_model = "H20"
hosts = ["dash3"]
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-b4-r2"]
[jobs.env]
TP = "4"
PROFILE_BATCH = "4"
SERVER_PORT = "9843"
OUTPUT_ROOT = "runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b4-r2"
FLASHINFER_WORKSPACE_BASE = "/tmp/frontier-component-flashinfer-v4"
[[jobs]]
name = "decode-grid-tp4-b6-r2-20260723"
gpus = 4
gpu_model = "H20"
hosts = ["dash4"]
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-b6-r2"]
[jobs.env]
TP = "4"
PROFILE_BATCH = "6"
SERVER_PORT = "9844"
OUTPUT_ROOT = "runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b6-r2"
FLASHINFER_WORKSPACE_BASE = "/tmp/frontier-component-flashinfer-v4"