Commit Graph

13 Commits

Author SHA1 Message Date
Li Wang
f8029945c3 [Bugfix] Remove cuda related lines and add additional pip mirror (#1252)
### What this PR does / why we need it?
- For npu environment, we should use `PYTORCH_NPU_ALLOC_CONF ` rather
than `PYTORCH_CUDA_ALLOC_CONF`
- Add `PIP_EXTRA_INDEX_URL` to make nightly_benchmarks happy


---------

Signed-off-by: wangli <wangli858794774@gmail.com>
2025-06-17 21:25:40 +08:00
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
Li Wang
37f4469a03 [CI][Benchmark] Add qwen2.5-7b test (#1104)
### What this PR does / why we need it?
- Add qwen2.5-7b performance benchmark, this is a sub pr of #1099, for
v1 test, need more verify
- Fix get commit time after checkout

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
2025-06-12 10:47:30 +08:00
Li Wang
dd207cb261 [CI][Benchmark] Add new model and v1 test to perf benchmarks (#1099)
### What this PR does / why we need it?
- Add qwen2.5-7b-instruct test
- Add v1 test
---------

Signed-off-by: wangli <wangli858794774@gmail.com>
2025-06-12 10:46:41 +08:00
wangxiyuan
4f5964420e [CI] Upgrade vllm to 0.9.1 (#1165)
1. upgrade vllm to 0.9.1. 0.9.0 is not supported for main branch now.
keep doc to 0.9.0 until we release the first 0.9.1 release.
2. disable V0 test for PR
3. move actionlint check to lint job

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-06-11 16:33:11 +08:00
Li Wang
b4cb0eecb6 [CI] Hotfix on benchmark results path (#1076)
### What this PR does / why we need it?
Fix benchmark results path

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

### How was this patch tested?
CI passed

Signed-off-by: wangli <wangli858794774@gmail.com>
2025-06-05 12:53:46 +08:00
Li Wang
31dd471574 [CI] Add workflow_dispatch and use main benchmarks directly (#1071)
### What this PR does / why we need it?

This is for the benchmark iteration, which will change the benchmark
scripts while checkouting each commit. So we need ensure the benchmark
scripts always available.

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

### How was this patch tested?
Manaully

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
2025-06-05 10:29:30 +08:00
Yikun Jiang
9e855b70be Adjust concurrency group for each npu workflow (#1068)
### What this PR does / why we need it?
Adjust concurrency group for each npu workflow
- for pd and benchmarks share the static-08-01, so only one job can runs
on
- other job one PR/schedule should have only 1 job runs

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

### How was this patch tested?
CI passed

Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
2025-06-05 09:17:04 +08:00
Li Wang
517811449e [CI] Re-enable sleep mode test and skip failure breaking CI (#990)
### What this PR does / why we need it?

- Re-enable sleep mode test
- Fix nightly performance benchmark workflow
- Fix model-runner-v1 bug for upstream
[change](https://github.com/vllm-project/vllm/pull/18654)
---------

Signed-off-by: wangli <wangli858794774@gmail.com>
2025-06-04 16:24:16 +08:00
Li Wang
eb2701e0b2 [CI] Remove workflow_dispatch and change schedule time (#1056)
### What this PR does / why we need it?

- Remove workflow_dispatch 
-  Change schedule time to 2:00 UTC+8
### Does this PR introduce _any_ user-facing change?


### How was this patch tested?
CI passed

---------

Signed-off-by: wangli <858794774@qq.com>
Co-authored-by: wangli <858794774@qq.com>
2025-06-04 01:19:20 +08:00
Li Wang
06fb5a8d81 [CI][Bugfix] Upgrade escli to v0.2.1 to fix benchmark deps (#1055)
### What this PR does / why we need it?

Update escli-tool to v.0.2.1 to fix deps bug

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

### How was this patch tested?
CI passed

Signed-off-by: wangli <858794774@qq.com>
2025-06-04 01:03:56 +08:00
Li Wang
76dacf3fa0 [CI][Benchmark] Optimize performance benchmark workflow (#1039)
### What this PR does / why we need it?

This is a post patch of #1014, for some convenience optimization
- Set cached dataset path for speed
- Use pypi to install escli-tool
- Add benchmark results convert script to have a developer-friendly
result
- Patch the `benchmark_dataset.py` to disable streaming load for
internet
- Add more trigger ways for different purpose, `pr` for debug,
`schedule` for daily test, `dispatch` and `pr-labled` for manual testing
of a single(current) commit
- Disable latency test for `qwen-2.5-vl`, (This script does not support
multi-modal yet)

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

### How was this patch tested?
CI passed

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
2025-06-03 23:38:34 +08:00
Li Wang
d9fb027068 [CI] Add benchmark workflows (#1014)
### What this PR does / why we need it?

Add benchmark workflows

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

### How was this patch tested?
Run locally

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
2025-05-30 22:42:44 +08:00