[ROCM][Perf] Add ROCM_SEGMENTED_ATTN attention-backend works across RDNA3/3.5/4 (#59132)
Signed-off-by: root <jeffaw99@hotmail.com> Signed-off-by: big-yellow-duck <jeffaw99@hotmail.com> Co-authored-by: Tan Pin Siang <1716735+tanpinsiang@users.noreply.github.com> Co-authored-by: vllmellm <190700713+vllmellm@users.noreply.github.com> Co-authored-by: Codex <noreply@openai.com>
This commit is contained in:
co-authored by
Tan Pin Siang
vllmellm
Codex
parent
15c1cc12ac
commit
edfccc9469
@@ -220,6 +220,13 @@ def kernel_warmup(worker: "Worker", *, process_local_only: bool = False):
|
||||
if process_local_only:
|
||||
return
|
||||
|
||||
if current_platform.is_rocm():
|
||||
from vllm.model_executor.warmup.rocm_segmented_attn_autotune_warmup import (
|
||||
rocm_segmented_attn_autotune_warmup,
|
||||
)
|
||||
|
||||
rocm_segmented_attn_autotune_warmup(worker)
|
||||
|
||||
flashinfer_sparse_mla_decode_autotune_warmup(worker)
|
||||
deepseek_v4_sparse_mla_attention_warmup(worker)
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user