[Attention] Integrate FlashAttention 4 SM100 headdim 256 support (#42669)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Matthew Bonanni
2026-07-27 18:25:50 +00:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent 8112b6c997
commit bf2b45b5d6
7 changed files with 66 additions and 34 deletions
@@ -1358,6 +1358,10 @@ def main():
profile_memory=args.profile_memory,
warmup_ms=args.warmup_ms,
prefill_backend=pb,
kv_lora_rank=args.kv_lora_rank,
qk_nope_head_dim=args.qk_nope_head_dim,
qk_rope_head_dim=args.qk_rope_head_dim,
v_head_dim=args.v_head_dim,
)
result = run_benchmark(config)