[ROCm][DSv3.2] Eliminate per-decode FillFunctor launches in sparse-MLA hot loop (#44527)
Signed-off-by: Frida Andersson <fanderss@amd.com>
This commit is contained in:
@@ -429,7 +429,6 @@ def rocm_fp8_paged_mqa_logits(
|
||||
(out_logits,) = current_workspace_manager().get_simultaneous(
|
||||
((batch_size * next_n, max_model_len), torch.float32),
|
||||
)
|
||||
out_logits.fill_(float("-inf"))
|
||||
deepgemm_fp8_paged_mqa_logits(
|
||||
q_fp8,
|
||||
kv_cache_fp8,
|
||||
@@ -715,7 +714,6 @@ def rocm_aiter_sparse_attn_indexer(
|
||||
scale_fmt,
|
||||
)
|
||||
|
||||
topk_indices_buffer[: hidden_states.shape[0]] = -1
|
||||
if has_prefill:
|
||||
prefill_metadata = layer_attn_metadata.prefill
|
||||
assert prefill_metadata is not None
|
||||
|
||||
Reference in New Issue
Block a user