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

[1/N][UT][v1 MTP] add basic v1 mtp features (#890)

Browse Source 
### What this PR does / why we need it?
add basic v1 mtp features
please merge it after
https://github.com/vllm-project/vllm-ascend/pull/874 and
https://github.com/vllm-project/vllm-ascend/pull/844.

### Does this PR introduce _any_ user-facing change?
now, we supported basic v1 mtp, only supported tp only、eager mode and
k=1
we will continue to expand more scenarios.

### How was this patch tested?
local tested

Signed-off-by: XWFAlone <xuewenfei2@huawei.com>
Co-authored-by: mengwei805 <mengwei25@huawei.com>
Co-authored-by: JC-ut0 <xuyexiong@huawei.com>
This commit is contained in:
XWFAlone
2025-05-30 08:59:58 +08:00
committed by GitHub
parent 5903547d09
commit 3442fbdb23
7 changed files with 477 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.github/workflows/vllm_ascend_test_long_term.yaml vendored
View File

@@ -93,6 +93,7 @@ jobs:
- name: Run vllm-project/vllm-ascend long term test
run: |
# spec decode test
VLLM_USE_MODELSCOPE=True pytest -sv tests/long_term/spec_decode/e2e/test_v1_mtp_correctness.py
VLLM_USE_MODELSCOPE=true pytest -sv tests/long_term/spec_decode/e2e/test_v1_spec_decode.py
VLLM_USE_MODELSCOPE=True pytest -sv tests/long_term/spec_decode/e2e/test_mtp_correctness.py # it needs a clean process
pytest -sv tests/long_term/spec_decode --ignore=tests/long_term/spec_decode/e2e/test_mtp_correctness.py --ignore=tests/long_term/spec_decode/e2e/test_v1_spec_decode.py
pytest -sv tests/long_term/spec_decode --ignore=tests/long_term/spec_decode/e2e/test_mtp_correctness.py --ignore=tests/long_term/spec_decode/e2e/test_v1_spec_decode.py --ignore=tests/long_term/spec_decode/e2e/test_v1_mtp_correctness.py