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

[Feat][SP] Suport SP for VL MoE models (#7044)

Browse Source 
### What this PR does / why we need it?

2nd PR for https://github.com/vllm-project/vllm-ascend/issues/5712,
extend SP to VL MoE models.


### Does this PR introduce _any_ user-facing change?
remove `sp_threshold` in additional config and reuse `sp_min_token_num`
from vLLM.


### How was this patch tested?
- Model: Qwen3-VL-30B-A3B, 
- TP4 DP2
- 100 reqs
- max concurrency 1

| Seq length | Mean TTFT (ms) main | Mean TTFT (ms) this PR |
|------------|---------------------|------------------------|
| 4k         | 429.40               | 323.3                  |
| 16k        | 1297.01              | 911.74                |

- vLLM version: v0.16.0
- vLLM main:
4034c3d32e

---------

Signed-off-by: realliujiaxu <realliujiaxu@163.com>
This commit is contained in:
realliujiaxu
2026-03-24 17:16:00 +08:00
committed by GitHub
parent 9615bc33fd
commit 5d12446573
21 changed files with 947 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/scripts/config.yaml vendored
View File

@@ -141,6 +141,8 @@ e2e-multicard-2-cards:
estimated_time: 164
- name: tests/e2e/multicard/2-cards/test_sp_pass.py
estimated_time: 198
- name: tests/e2e/multicard/2-cards/test_sequence_parallelism_moe.py
estimated_time: 120
e2e-multicard-4-cards:
- name: tests/e2e/multicard/4-cards/test_qwen3_next.py
estimated_time: 1868