[DP] Tiny fix of dp and update example (#1273)

### What this PR does / why we need it?
Add `max_num_tokens_across_dp` to AscendMetadata to fix dp

This pr fixes the bug introduced by
https://github.com/vllm-project/vllm-ascend/pull/1229, which add an arg
`max_num_tokens_across_dp` when dp_size > 1.

Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2025-06-25 11:03:04 +08:00
committed by GitHub
parent c1c5d56255
commit 52317f92cb
7 changed files with 327 additions and 172 deletions

View File

@@ -363,7 +363,10 @@ jobs:
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W8A8
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_dbo
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeekV3_dbo
pytest -sv tests/e2e/multicard/ --ignore=tests/e2e/multicard/test_ilama_lora_tp2.py --ignore=tests/e2e/multicard/test_offline_inference_distributed.py
pytest -sv tests/e2e/multicard/test_data_parallel.py
pytest -sv tests/e2e/multicard/ --ignore=tests/e2e/multicard/test_ilama_lora_tp2.py \
--ignore=tests/e2e/multicard/test_offline_inference_distributed.py \
--ignore=tests/e2e/multicard/test_data_parallel.py
- name: Run vllm-project/vllm-ascend test on V0 engine
if: ${{ github.event_name == 'schedule' }}
@@ -380,4 +383,7 @@ jobs:
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_topk
pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_W8A8
pytest -sv tests/e2e/multicard/ --ignore=tests/e2e/multicard/test_ilama_lora_tp2.py --ignore=tests/e2e/multicard/test_offline_inference_distributed.py
pytest -sv tests/e2e/multicard/test_data_parallel.py
pytest -sv tests/e2e/multicard/ --ignore=tests/e2e/multicard/test_ilama_lora_tp2.py \
--ignore=tests/e2e/multicard/test_offline_inference_distributed.py \
--ignore=tests/e2e/multicard/test_data_parallel.py