EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[CI] cleanup single/multi-card test (#5623)

Browse Source 
1. speed up e2e light test.
2. create `2-cards` and `4-cards` folder in multicard
3. move ops to nightly
4. run test in Alphabetical Order

- vLLM version: v0.13.0
- vLLM main:
8be6432bda

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2026-01-07 14:13:34 +08:00
committed by GitHub
parent 1afbc01ed4
commit 6f7a81cd9f
30 changed files with 114 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/e2e/singlecard/test_quantization.py
View File

@@ -46,7 +46,7 @@ def test_qwen3_w8a8_quant():
outputs_0_lst=vllm_target_outputs,
outputs_1_lst=vllm_quant_w8a8_outputs,
name_0="vllm_target_outputs",
name_1="vllm_w8a16_outputs",
name_1="vllm_quant_w8a8_outputs",
)
@@ -75,5 +75,5 @@ def test_qwen3_dense_w8a16():
outputs_0_lst=vllm_target_outputs,
outputs_1_lst=vllm_quant_w8a16_outputs,
name_0="vllm_target_outputs",
name_1="vllm_w8a16_outputs",
name_1="vllm_quant_w8a16_outputs",
)