[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:
co-authored by
gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent
8112b6c997
commit
bf2b45b5d6
@@ -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)
|
||||
|
||||
Reference in New Issue
Block a user