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

[Cherry Pick from pr#3981][0.11.0][P/D]Make kv-transfer env variable take effect & Fix load-balance proxy (#3983)

Browse Source 
### What this PR does / why we need it?
Make kv-transfer env variable take effect & Fix load-balance proxy.
Cherry Pick from #3981

---------
Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>
This commit is contained in:
zxr2333
2025-11-08 13:52:33 +08:00
committed by GitHub
parent 8e72758645
commit d4e2a44307
7 changed files with 35 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/disaggregated_prefill_v1/load_balance_proxy_layerwise_server_example.py
View File

@@ -561,9 +561,12 @@ async def metaserver(request: Request):
max_retries=global_args.max_retries,
base_delay=global_args.retry_delay)
proxy_state.release_prefiller(prefiller_idx, prefiller_score)
proxy_state.release_prefiller_kv(prefiller_idx,prefiller_score)
except Exception as e:
logger.error(f"Post metaserver failed with: {str(e)}")
proxy_state.release_prefiller(prefiller_idx, prefiller_score)
proxy_state.release_prefiller_kv(prefiller_idx, prefiller_score)
if __name__ == '__main__':