[Attention][MiniMax-M3] NVFP4 KV cache on the MSA sparse attention path (#59300)

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Yongye Zhu
2026-10-01 14:39:55 -07:00
committed by GitHub
co-authored by Claude Opus 5.5
parent ea84051819
commit 7566d83bd3
12 changed files with 1297 additions and 73 deletions
+2 -1
View File
@@ -513,7 +513,8 @@ STABLE_TORCH_LIBRARY_FRAGMENT(_C, ops) {
"Tensor!? kv_cache, Tensor!? index_cache, "
"int block_size, Tensor!? q_out, Tensor!? index_q_out, "
"str kv_cache_dtype, bool skip_index_branch=False, "
"Tensor!? q_fp8_out=None, float q_fp8_scale=1.0) -> ()");
"Tensor!? q_fp8_out=None, float q_fp8_scale=1.0, "
"Tensor? kv_k_scale=None, Tensor? kv_v_scale=None) -> ()");
#ifdef VLLM_ENABLE_FUSED_KDA_DECODE
ops.def(