starmountain1997 248d07566f [CI] nightly test timeout (#6912) ...

### What this PR does / why we need it?

The nightly test is currently failing due to a
[timeout](https://github.com/vllm-project/vllm-ascend/actions/runs/22547280169/job/65326335134).

As noted in #6778, this issue can be resolved by applying this fix.

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

no

### How was this patch tested?

run nightly test.

Co-authored-by: guozr <guozr1997@hotmail.com>

2026-03-03 09:31:46 +08:00

..

__init__.py

[1/N] Refactor nightly test structure (#5479)

2025-12-30 19:03:02 +08:00

test_deepseek_r1_0528_w8a8_eplb.py

[EPLB][Nightly] Refactor UT (#6543)

2026-02-14 10:56:29 +08:00

test_deepseek_r1_0528_w8a8.py

[EPLB][Nightly] Refactor UT (#6543)

2026-02-14 10:56:29 +08:00

test_deepseek_r1_w8a8_hbm.py

[CI] Add DeepSeek-V3.2-W8A8 nightly ci test (#4633)

2026-01-20 21:05:15 +08:00

test_deepseek_v3_2_w8a8.py

[CI] nightly test timeout (#6912)

2026-03-03 09:31:46 +08:00

test_glm4_5.py

[Feature] GLM4.6 support mtp with fullgraph (#5460)

2026-01-09 16:07:42 +08:00

test_kimi_k2_thinking.py

[CI]Add Kimi k2 nightly test (#5682)

2026-01-12 15:56:07 +08:00

test_mtpx_deepseek_r1_0528_w8a8.py

[1/N] Refactor nightly test structure (#5479)

2025-12-30 19:03:02 +08:00

test_prefix_cache_deepseek_r1_0528_w8a8.py

[1/N] Refactor nightly test structure (#5479)

2025-12-30 19:03:02 +08:00

test_prefix_cache_qwen3_32b_int8.py

[1/N] Refactor nightly test structure (#5479)

2025-12-30 19:03:02 +08:00

test_qwen2_5_vl_7b_epd.py

[Test] Add initial multi modal cases of Qwen2.5-VL-7B-Instruct for disaggregated encoder (#5301)

2026-02-06 17:30:17 +08:00

test_qwen2_5_vl_7b.py

[1/N] Refactor nightly test structure (#5479)

2025-12-30 19:03:02 +08:00

test_qwen2_5_vl_32b.py

[1/N] Refactor nightly test structure (#5479)

2025-12-30 19:03:02 +08:00

test_qwen3_30b_w8a8.py

[1/N] Refactor nightly test structure (#5479)

2025-12-30 19:03:02 +08:00

test_qwen3_32b_int8_a3_feature_stack3.py

[Refactor] MLP weight prefetch to consistency with MoE Model's prefetching in terms of code and usage (#6442)

2026-02-04 09:08:18 +08:00

test_qwen3_32b_int8.py

[CI] Change A2 runner (#6557)

2026-02-05 23:43:57 +08:00

test_qwen3_32b.py

[1/N] Refactor nightly test structure (#5479)

2025-12-30 19:03:02 +08:00

test_qwen3_235b_a22b_w8a8_eplb.py

[EPLB][Nightly] Refactor UT (#6543)

2026-02-14 10:56:29 +08:00

test_qwen3_235b_w8a8.py

[EPLB][Nightly] Refactor UT (#6543)

2026-02-14 10:56:29 +08:00

test_qwen3_next_w8a8.py

[CI] Accuracy issue of qwen3-next-w8a8 nightly test fix. (#5746)

2026-01-09 15:55:13 +08:00

test_qwen3_next.py

[CI] Change A2 runner (#6557)

2026-02-05 23:43:57 +08:00

test_qwq_32b.py

[Refactor] MLP weight prefetch to consistency with MoE Model's prefetching in terms of code and usage (#6442)

2026-02-04 09:08:18 +08:00