[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:
Dakai An
2026-10-09 15:48:37 -04:00
committed by GitHub
co-authored by Yifan Qiao OpenAI Codex OpenAI Codex Lucas Wilkinson Claude Opus 5.5 Lucas Wilkinson
parent 3766a67a32
commit 02e55d2af3
83 changed files with 1280 additions and 1986 deletions
@@ -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):