-
Notifications
You must be signed in to change notification settings - Fork 460
Refactor e2e CI #2276
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Refactor e2e CI #2276
Conversation
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:
If CI fails, you can run linting and testing checks locally according Contributing and Testing. |
fb88b90
to
7983418
Compare
1ff0e9e
to
46d8efa
Compare
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #2276 +/- ##
=======================================
Coverage 73.49% 73.49%
=======================================
Files 151 151
Lines 21927 21927
=======================================
Hits 16116 16116
Misses 5811 5811
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
46d8efa
to
9ea433c
Compare
def test_deepseek_raises_error(monkeypatch: pytest.MonkeyPatch) -> None: | ||
with monkeypatch.context() as m: | ||
m.setenv("VLLM_USE_MODELSCOPE", "True") | ||
with pytest.raises(NotImplementedError) as excinfo: | ||
VllmRunner("deepseek-ai/DeepSeek-V2-Lite-Chat", | ||
max_model_len=1024, | ||
enforce_eager=False) | ||
assert "ACL Graph does not support deepseek" in str(excinfo.value) | ||
|
||
|
||
@pytest.mark.parametrize("model", MODELS) | ||
def test_ray_backend_sets_no_compilation(model: str) -> None: | ||
runner = VllmRunner(model, | ||
enforce_eager=False, | ||
distributed_executor_backend="ray") | ||
assert runner.model.llm_engine.vllm_config.compilation_config.level == 0 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Need to move to ut
tests/e2e/singlecard/test_chunked.py
Outdated
temperature=0.0, | ||
) | ||
|
||
vllm_model = LLM(model, long_prefill_token_threshold=4, enforce_eager=True) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Seems need to keep: #1172
assert torch.all(tensor == pynccl_comm.world_size).cpu().item() | ||
|
||
|
||
def test_pyhccl(): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
better to keep pyhccl e2e test if no more time cost, we can remove this after pyhccl removed
be01f15
to
0e2b140
Compare
b6a3d08
to
0a8fe5f
Compare
de360ff
to
6907a94
Compare
e523103
to
65767d7
Compare
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
65767d7
to
8a60f2b
Compare
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
8a60f2b
to
44d0d19
Compare
44d0d19
to
c00f0da
Compare
It seems that the error in this e2e, #2675 can be resolved. |
ba08c9e
to
3045a1a
Compare
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
3045a1a
to
95b11ff
Compare
CI is blocked for quite long time. Let's merge this first and then recover the failure test asap. |
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: vllm-project/vllm@a344a5a Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: hfadzxy <starmoon_zhang@163.com>
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: vllm-project/vllm@a344a5a Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: hfadzxy <starmoon_zhang@163.com>
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: vllm-project/vllm@a344a5a Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: hfadzxy <starmoon_zhang@163.com>
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: vllm-project/vllm@a344a5a Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: hfadzxy <starmoon_zhang@163.com>
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: vllm-project/vllm@a344a5a Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: offline0806 <z00858301@china.huawei.com>
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: vllm-project/vllm@a344a5a Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
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: vllm-project/vllm@a344a5a Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Refactor E2E CI to make it clear and faster