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

[Bugfix] fix dp parallel + tp > 1 offline inference port conflict (#4539)

Browse Source 
### What this PR does / why we need it?
fix dp parallel + tp > 1 offline inference port conflict

issue import PR:https://github.com/vllm-project/vllm-ascend/pull/429


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

---------

Signed-off-by: leo-pony <nengjunma@outlook.com>
This commit is contained in:
Nengjun Ma
2025-11-29 18:37:11 +08:00
committed by GitHub
parent 1874265074
commit a3041cd78c
3 changed files with 53 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.github/workflows/_e2e_test.yaml vendored
View File

@@ -269,6 +269,7 @@ jobs:
tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W4A8DYNAMIC
# tests/e2e/multicard/test_qwen3_moe.py::test_models_distributed_Qwen3_MOE_TP2_WITH_EP \
# tests/e2e/multicard/test_qwen3_moe.py::test_models_distributed_Qwen3_MOE_W8A8_WITH_EP
pytest -sv tests/e2e/multicard/test_data_parallel_tp2.py
- name: Install Ascend toolkit & triton_ascend (for Qwen3-Next-80B-A3B-Instruct)
shell: bash -l {0}