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

[P/D][BugFix]Fix proxy format processing errors & Layerwise connector performance optimization (#4043)

Browse Source 
### What this PR does / why we need it?
1. Fix proxy format processing errors.
2. Layer-wise connector performance optimization.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
By CI.

- vLLM version: v0.11.0
- vLLM main:
83f478bb19

---------

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>
Co-authored-by: wangxiaoteng <wangxiaoteng@huawei.com>
This commit is contained in:
zxr2333
2025-11-08 18:44:06 +08:00
committed by GitHub
parent 24d6314718
commit 1d81a289d0
3 changed files with 16 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/disaggregated_prefill_v1/load_balance_proxy_layerwise_server_example.py
View File

@@ -447,7 +447,7 @@ def get_api_request_id(api, req_id):
def get_origin_request_id(api, req_id):
if api == "/completions":
return req_id.replace("cmpl-", "").replace("-0", "")
return req_id.replace("cmpl-", "")[:-2]
elif api == "/chat/completions":
return req_id.replace("chatcmpl-", "")