fix: wait for HiCache load-back before hybrid MLA KV reads (#38217)
Co-authored-by: zhouzechun <zhouzechun@kuaishou.com> Co-authored-by: alphabetc1 <2508695655@qq.com>
This commit is contained in:
co-authored by
zhouzechun
alphabetc1
parent
9336681310
commit
156d54e56c
@@ -4502,6 +4502,8 @@ class HybridLinearKVPool(KVCache):
|
||||
dst_dtype: Optional[torch.dtype] = None,
|
||||
):
|
||||
assert self.use_mla, "get_mla_kv_buffer called when use_mla is False"
|
||||
# Wait for HiCache load-back here; the inner pool's counter is disabled.
|
||||
self._wait_for_layer(layer.layer_id)
|
||||
# Read door -- same physical-id contract as the write door: `loc` is
|
||||
# a read-index tensor already translated at its production site
|
||||
# (fetch_mha_one_shot_kv_indices / prepare_chunked_kv_indices); the
|
||||
|
||||
Reference in New Issue
Block a user