[KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai> Signed-off-by: Dakai An <dakaian108@gmail.com> Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com> Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai> Co-authored-by: OpenAI Codex <noreply@openai.com> Co-authored-by: OpenAI Codex <codex@openai.com> Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com> Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
This commit is contained in:
co-authored by
Yifan Qiao
OpenAI Codex
OpenAI Codex
Lucas Wilkinson
Claude Opus 5.5
Lucas Wilkinson
parent
3766a67a32
commit
02e55d2af3
@@ -1376,14 +1376,6 @@ class MLAAttention(nn.Module, AttentionLayerBase):
|
||||
is_index_group_leader=self.indexer is not None,
|
||||
non_causal_multi_token_decode=self.non_causal_multi_token_decode,
|
||||
)
|
||||
# SM100 FlashMLA paged kernels also express TMA coordinates in token rows.
|
||||
uses_tma_rows = (
|
||||
self.attn_backend.get_name() == "FLASHMLA_SPARSE"
|
||||
and self.kv_cache_dtype in ("fp8_ds_mla", "nvfp4_ds_mla")
|
||||
and current_platform.is_device_capability_family(100)
|
||||
)
|
||||
if self._uses_flat_kv_cache() or uses_tma_rows:
|
||||
spec = replace(spec, block_stride_alignment=spec.state_content_size_bytes)
|
||||
return spec
|
||||
|
||||
def _v_up_proj(self, x: torch.Tensor, out: torch.Tensor):
|
||||
|
||||
Reference in New Issue
Block a user