Commit Graph

5 Commits

Author SHA1 Message Date
Mengqing Cao
96fa7ff63b [DP][V1] Fix rank set in DP scenario & Bump torch-npu version to 2.5.1.post1.dev20250528 (#1235)
### What this PR does / why we need it?
1. Fix rank set in DP scenario. The new poc version of torch-npu support
setting `ASCEND_RT_VISIBLE_DEVICES` dynamically, thus we could use the
rank set in `DPEngineCoreProc` directly instead of calculating local
rank across dp by hand in the patched `_init_data_parallel`

Closes: https://github.com/vllm-project/vllm-ascend/issues/1170

2. Bump torch-npu version to 2.5.1.post1.dev20250528

Closes: https://github.com/vllm-project/vllm-ascend/pull/1242
Closes: https://github.com/vllm-project/vllm-ascend/issues/1232


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

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: Icey <1790571317@qq.com>
Co-authored-by: Icey <1790571317@qq.com>
2025-06-16 23:09:53 +08:00
Yikun Jiang
966557a2a3 [Build] Speedup image build (#1216)
### What this PR does / why we need it?
1. Rename workflow name to show OS info
2. Speedup image build:
- PR: only arm64 build on openEuler arm64, only amd64 build on Ubuntu
amd64
- Push/Tag: still keep origin logic use qemu on amd64

This PR actually drop the e2e image build per PR but I think it's fine
consider it's stable enough, if we still meet some problem we can revert
this PR

43-44mins ---> about 8-10 mins

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
CI passed

Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
2025-06-16 09:02:53 +08:00
Mengqing Cao
399b03830d [Build][Bugfix] Fix source code path to avoid reference error (#726)
### What this PR does / why we need it?
Fix source code path to avoid reference error in docker image
fix https://github.com/vllm-project/vllm-ascend/issues/725

Signed-off-by: MengqingCao <cmq0113@163.com>
2025-04-30 17:38:13 +08:00
Yikun Jiang
96d6fa7c90 [Docker] Fix openEuler image suffix (#586)
### What this PR does / why we need it?
There was a bug when we release v0.8.4rc1 (openEuler image tag was wrong
set to 0.8.4rc1), according doc of docker-meta-action, it should be
append suffix:
```
tags: |
  type=pep440,enable=true,priority=900,prefix=,suffix=,pattern=,value=
```

This patch just fix openEuler image suffix to make pep440 tag rule work.

This patch also remove the cache step because the cache step bring more
than 10mins export, but reduce less time in next trigger.

### Does this PR introduce _any_ user-facing change?
Yes, docker image tag set to right

### How was this patch tested?
I test with in my fork repo by setting default branch:
- release a tag: v0.7.88rc1 (pep440 tag)
- The log show `--label
org.opencontainers.image.version=v0.7.88rc1-openeuler` is right rule


https://github.com/Yikun/vllm-ascend/actions/runs/14560411481/job/40842950165#step:9:205

Related: https://github.com/vllm-project/vllm-ascend/pull/489

Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
2025-04-21 08:55:26 +08:00
wangxiyuan
9c7428b3d5 [CI] enable custom ops build (#466)
### What this PR does / why we need it?
This PR enable custom ops build  by default. 

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

Yes, users now install vllm-ascend from source will trigger custom ops
build step.

### How was this patch tested?
By image build and e2e CI

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-04-12 10:24:53 +08:00