Gahow Wang adaf68badc Add full per-TP FlashAttention profile sweep

2026-07-16 21:24:11 +08:00

..

experiment-card.md

Add vLLM 0.20 per-TP FlashAttention profile smoke

2026-07-16 21:00:27 +08:00

extract_trace_profile_support.py

Freeze Qwen30 trace profile support

2026-07-16 21:09:51 +08:00

fleet.toml

Add vLLM 0.20 per-TP FlashAttention profile smoke

2026-07-16 21:00:27 +08:00

jobs_flashattn_full.toml

Add full per-TP FlashAttention profile sweep

2026-07-16 21:24:11 +08:00

jobs_smoke.toml

Retry profile smoke with cu129 vLLM wheel

2026-07-16 21:19:22 +08:00

mock-profile-ablation.png

Add vLLM 0.20 per-TP FlashAttention profile smoke

2026-07-16 21:00:27 +08:00

plot_mock_ablation.py

Add vLLM 0.20 per-TP FlashAttention profile smoke

2026-07-16 21:00:27 +08:00

profile_vllm020_flashattn.py

Serialize vLLM attention profile results

2026-07-16 21:17:27 +08:00

run_flashattn_full.sh

Add full per-TP FlashAttention profile sweep

2026-07-16 21:24:11 +08:00

run_flashattn_smoke.sh

Add vLLM 0.20 per-TP FlashAttention profile smoke

2026-07-16 21:00:27 +08:00