Commit Graph

10 Commits

Author SHA1 Message Date
Icey
2a9d02e080 [Bugfix] eagle and eagle3 spec decode failures and enable e2e test (#2979)
### What this PR does / why we need it?
- Fix the bug https://github.com/vllm-project/vllm-ascend/issues/2978
- Enable e2e test,
- Adapt to scenarios where Speculative tokens are greater than 2,
- Fix the bug that causes Eagle3 inference failures under high
concurrency and improve the acceptance rate of draft models, by
https://github.com/vllm-project/vllm-ascend/pull/2794

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?
CI passed with new added/existing test.

Co-authored-by: hukongyi
[hukongyi@cmbchina.com](mailto:hukongyi@cmbchina.com)
Co-authored-by: guanyuzhu
[zhuguanyu@huawei.com](mailto:zhuguanyu@huawei.com)
Co-authored-by: liumail680
[liumail680@163.com](mailto:liumail680@163.com)


- vLLM version: v0.10.2
- vLLM main:
f225ea7dd9

---------

Signed-off-by: Icey <1790571317@qq.com>
2025-09-25 14:39:12 +08:00
xuyexiong
6681dde902 [Feat][Graph] Support MTP for ACL Graph (#2932)
### What this PR does / why we need it?
This PR depends on the merge of #2707 and has adapted the aclgraph
functionality to support MTP.

### How was this patch tested?


- vLLM version: v0.10.2
- vLLM main:
2b85697031

---------

Signed-off-by: xuyexiong <xuyexiong@huawei.com>
2025-09-18 14:05:33 +08:00
1092626063
5b3646ab21 [FEATURE][MTP] Support MTP > 1 (#2708)
### What this PR does / why we need it?
[RFC:Support MTP > 1 for
DeepSeek](https://github.com/vllm-project/vllm-ascend/issues/2745)

- [x] dp1 tp16
- [x] dp4 tp4
- [x] dp2 tp 8
- [x] torchair graph

- vLLM version: v0.10.1.1
- vLLM main:
c9f7081f9c

Signed-off-by: 1092626063 <1092626063@qq.com>
2025-09-05 09:11:22 +08:00
wangxiyuan
24d4dad7b2 [CI] Enable MTP torchair e2e test (#2705)
enable MTP torchair e2e test

- vLLM version: v0.10.1.1
- vLLM main:
ce30dca5c4

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-09-03 08:57:43 +08:00
xuyexiong
214b32a346 [V1][BUGFIX][0.10.1] FIX mtp on main branch (#2632)
### What this PR does / why we need it?
Fix MTP torchair bug caused by torchair refactor and moe refactor

Depends on PRs:
fused moe fix: https://github.com/vllm-project/vllm-ascend/pull/2627 
torchair multi DP fix:
https://github.com/vllm-project/vllm-ascend/pull/2626

### Does this PR introduce _any_ user-facing change?
when dp is enabled, to run mtp online server, need to disable server log
due to the current metrics does not support multi dp
`--disable-log-stats`
### How was this patch tested?


- vLLM version: v0.10.1.1
- vLLM main:
7c8271cd1e

Signed-off-by: xuyexiong <xuyexiong@huawei.com>
2025-09-02 11:12:41 +08:00
wangxiyuan
fef18b60bc Refactor e2e CI (#2276)
Refactor E2E CI to make it clear and faster
1. remove some uesless e2e test
2. remove some uesless function
3. Make sure all test runs with VLLMRunner to avoid oom error
4. Make sure all ops test end with torch.empty_cache to avoid oom error
5. run the test one by one to avoid resource limit error


- vLLM version: v0.10.1.1
- vLLM main:
a344a5aa0a

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-09-02 09:02:22 +08:00
ZhaoJiangJiang
3629bc4431 feat: add mtp ut and fix some bugs (#2453)
### What this PR does / why we need it?
Fix mtp mode ut

### Does this PR introduce _any_ user-facing change?
Nothing

### How was this patch tested?
This can be tested in the same way as a unit test.


- vLLM version: v0.10.0
- vLLM main:
53415653ff

Signed-off-by: 赵江江 <zhaojiangjiang1@h-partners.com>
Co-authored-by: 赵江江 <zhaojiangjiang1@h-partners.com>
2025-08-22 17:09:08 +08:00
wangxiyuan
9260910c8d [CI] Fix broken CI (#2302)
1. disable test_eagle_ccorrectness test, we'll reopen it once oom error
fixed.
2. drop transformers version limit for main, since vLLM rely on
>=4.55.0, see:
65552b476b
3. fix kv_connector_output bug, see:
796bae07c5

- vLLM version: v0.10.0
- vLLM main:
d1af8b7be9

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-08-11 11:22:32 +08:00
wangxiyuan
787010a637 [Test] Remove VLLM_USE_V1 in example and tests (#1733)
V1 is enabled by default, no need to set it by hand now. This PR remove
the useless setting in example and tests

- vLLM version: v0.9.2
- vLLM main:
9ad0a4588b

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-07-15 12:49:57 +08:00
Mengqing Cao
dd22ac38b2 [CI/UT][Refactor] move e2e spec decode and deepseek acc test to per pr (#1136)
### What this PR does / why we need it?
1. run deepseek acc ut per pr --- multicard CI time increased by 9 min
2. run spec decode e2e test on v1 per pr --- singlecard CI time
increased by 3 min (partly is disabled due to not work now)
~~3. align the output of whether dbo is enabled or not~~
    The generated results with and without dbo cannot be aligned.

https://github.com/vllm-project/vllm-ascend/actions/runs/15822900528/job/44600029405?pr=1136
4. skip V0 mtp test due to failure in
https://github.com/vllm-project/vllm-ascend/actions/runs/16012172833/job/45171988816
5. fix some version conflicts
### How was this patch tested?
CI passed with new added test.

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
2025-07-04 18:05:45 +08:00