Files
aituner/runs/frontier-decode-batch-grid-v0/jobs-grid-r1b.toml

47 lines
1.5 KiB
TOML

version = 1
[[jobs]]
name = "decode-grid-tp2-b6-r1-20260723"
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-b6-r1"]
[jobs.env]
TP = "2"
PROFILE_BATCH = "6"
SERVER_PORT = "9845"
OUTPUT_ROOT = "runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b6-r1"
FLASHINFER_WORKSPACE_BASE = "/tmp/frontier-component-flashinfer-v4"
[[jobs]]
name = "decode-grid-tp2-b8-r1-20260723"
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-b8-r1"]
[jobs.env]
TP = "2"
PROFILE_BATCH = "8"
SERVER_PORT = "9846"
OUTPUT_ROOT = "runs/frontier-decode-batch-grid-v0/remote-outputs/tp2-b8-r1"
FLASHINFER_WORKSPACE_BASE = "/tmp/frontier-component-flashinfer-v4"
[[jobs]]
name = "decode-grid-tp4-b8-r1-20260723"
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-b8-r1"]
[jobs.env]
TP = "4"
PROFILE_BATCH = "8"
SERVER_PORT = "9847"
OUTPUT_ROOT = "runs/frontier-decode-batch-grid-v0/remote-outputs/tp4-b8-r1"
FLASHINFER_WORKSPACE_BASE = "/tmp/frontier-component-flashinfer-v4"