44 lines
1.7 KiB
TOML
44 lines
1.7 KiB
TOML
# Append-only queue for the simulator-fidelity v1 campaign.
|
|
version = 1
|
|
|
|
[[jobs]]
|
|
name = "qwen235b-t0-tp4-smoke-20260716-v1"
|
|
gpus = 4
|
|
gpu_model = "H20"
|
|
hosts = ["dash0"]
|
|
command = "timeout --signal=TERM --kill-after=60s 1800 bash run_t0_smoke.sh"
|
|
artifacts = ["artifacts/t0-smoke-20260716"]
|
|
|
|
[jobs.env]
|
|
OUTPUT_ROOT = "/home/admin/cpfs/wjh/aituner/aituner-fidelity-v1/artifacts/t0-smoke-20260716"
|
|
VENV_ROOT = "/tmp/wjh-frontier-vllm0102-smoke/.venv"
|
|
MODEL_ROOT = "/home/admin/cpfs/wjh/models/Qwen/Qwen3-235B-A22B-FP8"
|
|
FRONTIER_ROOT = "/home/admin/cpfs/wjh/frontier-community-qwen235-smoke-20260715/Frontier-d9cfeb6"
|
|
SERVER_PORT = "18910"
|
|
|
|
[[jobs]]
|
|
name = "qwen235b-decode-attention-profile-20260716-v1"
|
|
gpus = 1
|
|
gpu_model = "H20"
|
|
hosts = ["dash0"]
|
|
command = "timeout --signal=TERM --kill-after=30s 900 bash run_decode_attention_profile.sh"
|
|
artifacts = ["artifacts/decode-attention-profile-20260716"]
|
|
|
|
[jobs.env]
|
|
OUTPUT_ROOT = "/home/admin/cpfs/wjh/aituner/aituner-fidelity-v1/artifacts/decode-attention-profile-20260716"
|
|
VENV_ROOT = "/tmp/wjh-frontier-vllm0102-smoke/.venv"
|
|
FRONTIER_ROOT = "/home/admin/cpfs/wjh/frontier-community-qwen235-smoke-20260715/Frontier-d9cfeb6-best-effort-v6-batched-lanes-r3"
|
|
|
|
[[jobs]]
|
|
name = "qwen235b-t0-full-attention-profile-20260716-v1"
|
|
gpus = 1
|
|
gpu_model = "H20"
|
|
hosts = ["dash0"]
|
|
command = "timeout --signal=TERM --kill-after=30s 900 bash run_t0_full_attention_profile.sh"
|
|
artifacts = ["artifacts/t0-full-attention-profile-20260716"]
|
|
|
|
[jobs.env]
|
|
OUTPUT_ROOT = "/home/admin/cpfs/wjh/aituner/aituner-fidelity-v1/artifacts/t0-full-attention-profile-20260716"
|
|
VENV_ROOT = "/tmp/wjh-frontier-vllm0102-smoke/.venv"
|
|
FRONTIER_ROOT = "/home/admin/cpfs/wjh/frontier-community-qwen235-smoke-20260715/Frontier-d9cfeb6-best-effort-v6-batched-lanes-r3"
|