[Attention] Abstract the MLA prefill backends and eliminate cuDNN (#32623)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com> Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com> Co-authored-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
Michael Goin
Lucas Wilkinson
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
51295793a2
commit
f3fef12350
@@ -333,8 +333,6 @@ def test_attention_config():
|
||||
"true",
|
||||
"--attention-config.flash_attn_max_num_splits_for_cuda_graph",
|
||||
"16",
|
||||
"--attention-config.use_cudnn_prefill",
|
||||
"true",
|
||||
"--attention-config.use_trtllm_ragged_deepseek_prefill",
|
||||
"true",
|
||||
"--attention-config.use_trtllm_attention",
|
||||
@@ -352,7 +350,6 @@ def test_attention_config():
|
||||
assert engine_args.attention_config.flash_attn_version == 3
|
||||
assert engine_args.attention_config.use_prefill_decode_attention is True
|
||||
assert engine_args.attention_config.flash_attn_max_num_splits_for_cuda_graph == 16
|
||||
assert engine_args.attention_config.use_cudnn_prefill is True
|
||||
assert engine_args.attention_config.use_trtllm_ragged_deepseek_prefill is True
|
||||
assert engine_args.attention_config.use_trtllm_attention is True
|
||||
assert engine_args.attention_config.disable_flashinfer_prefill is True
|
||||
|
||||
Reference in New Issue
Block a user