3 Commits

Author	SHA1	Message	Date
Shaoxu Cheng	1ffca8673f	[Feature]: Support 310P device run qwen2.5/3 dense and qwen2.5vl models (#5776) ... ### What this PR does / why we need it? Add basic 310p support. Only dense models work with eager mode now. - vLLM version: v0.13.0 - vLLM main: 2f4e6548ef --------- Signed-off-by: Tflowers-0129 <2906339855@qq.com> Signed-off-by: Shaoxu Cheng <2906339855@qq.com>	2026-01-17 11:49:18 +08:00
wangxiyuan	a25209252f	[CI] Add 310p e2e test back (#5797) ... This PR add 310 e2e test back to ensure the related PR will be tested on 310. 1. for light e2e, we'll run 310p test if the changed files are located in `vllm_ascend/_310p` 2. for full e2e, we'll always run 310p test 3. for main2main test, we'll stop run 310p test - vLLM version: v0.13.0 - vLLM main: 2f4e6548ef Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>	2026-01-15 15:47:13 +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