[Kernel][DSv4.1] Bump FlashMLA to the 2026.09.30 release and its interleaved V4.1 KV cache (#61371)

Signed-off-by: juntianl <juntianl@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Kimi Code <noreply@moonshot.ai>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
This commit is contained in:
Juntian Liu
2026-10-15 13:58:25 -07:00
committed by GitHub
co-authored by Claude Opus 5.5 Kimi Code Yifan Qiao
parent 33212db2c2
commit f8460ef236
13 changed files with 262 additions and 165 deletions
+1 -1
View File
@@ -948,7 +948,7 @@ def fp8_fp4_paged_sparse_mqa_logits(
Args:
q: ``(q_values, q_scale)``; q_values is [num_q_tokens, 1, H, D].
kv_cache: Fused paged cache [num_pages, page_kv, 1, D' + 4] uint8,
page stride 512B-aligned.
page stride 256B-aligned.
weights: [num_q_tokens, H] ``torch.bfloat16``.
metadata: From `get_paged_sparse_mqa_logits_metadata`.
num_max_sparse_blocks: Candidate blocks per row.