[GLM5.3 Bug] Fix sparse indexer attn topk backend selection (#58594)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
@@ -495,6 +495,7 @@ class DeepseekV32Attention(MLAAttention):
|
|||||||
self._vllm_config.parallel_config.cp_kv_cache_interleave_size
|
self._vllm_config.parallel_config.cp_kv_cache_interleave_size
|
||||||
),
|
),
|
||||||
skip_topk_buffer_clear=True,
|
skip_topk_buffer_clear=True,
|
||||||
|
topk_backend=self.indexer.indexer_op.topk_backend,
|
||||||
)
|
)
|
||||||
self.impl.record_logical_topk_ready() # type: ignore[attr-defined]
|
self.impl.record_logical_topk_ready() # type: ignore[attr-defined]
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user