[ROCm][MiniMax-M3] Add AITER sparse paged attention (#47287)
Signed-off-by: Tan Pin Siang <tanpinsiang@gmail.com> Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com> Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com> Co-authored-by: Hongxia Yang <hongxia.yang@amd.com> Co-authored-by: Jun Kang Chow <junkangchow@gmail.com> Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
This commit is contained in:
co-authored by
vllmellm
Hongxia Yang
Jun Kang Chow
tjtanaa
parent
e26264f3ef
commit
ee5a89f4d7
@@ -466,7 +466,7 @@ STABLE_TORCH_LIBRARY_FRAGMENT(_C, ops) {
|
||||
"Tensor? slot_mapping, Tensor? index_slot_mapping, "
|
||||
"Tensor!? kv_cache, Tensor!? index_cache, "
|
||||
"int block_size, Tensor!? q_out, Tensor!? index_q_out, "
|
||||
"str kv_cache_dtype) -> ()");
|
||||
"str kv_cache_dtype, bool skip_index_branch=False) -> ()");
|
||||
|
||||
// Apply repetition penalties to logits in-place.
|
||||
ops.def(
|
||||
|
||||
Reference in New Issue
Block a user