EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[BugFix][0.18.0] Remove unused layers assignment in mooncake connector (#8602)

Browse Source 
### What this PR does / why we need it?
Remove unused layers assignment in mooncake connector

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?
by nightly

Signed-off-by: liziyu <liziyu16@huawei.com>
This commit is contained in:
liziyu
2026-04-23 14:08:53 +08:00
committed by GitHub
parent 30d08ced2d
commit 58c87bd15b
1 changed files with 0 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake_connector.py
View File

@@ -586,7 +586,6 @@ class KVCacheRecvingThread(threading.Thread):
head_dim = self.model_config.hf_text_config.head_dim
block_size = self.vllm_config.cache_config.block_size
num_kv_head = max(self.model_config.hf_text_config.num_key_value_heads // self.tp_size, 1)
layers = self.model_config.hf_text_config.num_hidden_layers
layers = len(self.kv_caches)
flat_block_ids = [item for sublist in block_ids for item in sublist]
block_ids_tensor = torch.tensor(flat_block_ids, dtype=torch.int64, device=device)