Donato Capitella 1ddcb9a202 feat: Configure ROCm attention via --attention-backend CLI argument, disable the Ray dashboard, and make eager mode configurable for cluster benchmarks.

2026-02-02 15:40:16 +00:00

..

benchmark_results

updates

2025-12-20 11:37:06 +00:00

benchmark_results_rocm_attn/benchmark_results

added ROCm/Triton attention comparison

2025-12-20 11:49:03 +00:00

find_max_context.py

feat: Optimize model max_num_seqs and global benchmark parameters for Strix Halo, and centralize configurations in models.py.

2026-02-02 08:45:13 +00:00

max_context_results.json

updating max context results

2026-02-02 11:56:26 +00:00

run_vllm_bench.py

feat: Configure ROCm attention via --attention-backend CLI argument, disable the Ray dashboard, and make eager mode configurable for cluster benchmarks.

2026-02-02 15:40:16 +00:00

vllm_cluster_bench.py

feat: Configure ROCm attention via --attention-backend CLI argument, disable the Ray dashboard, and make eager mode configurable for cluster benchmarks.

2026-02-02 15:40:16 +00:00