wangxiyuan 830332ebfc Clean up v0.9.1 code (#1672) ...

vllm has released 0.9.2. This PR drop 0.9.1 support.

- vLLM version: v0.9.1
- vLLM main:
b942c094e3

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

2025-07-09 08:52:24 +08:00

..

test_data_parallel.py

[DP] Tiny fix of dp and update example (#1273)

2025-06-25 11:03:04 +08:00

test_deepseek_v2_lite_tp2_accuracy.py

[CI/UT][Refactor] move e2e spec decode and deepseek acc test to per pr (#1136)

2025-07-04 18:05:45 +08:00

test_dynamic_npugraph_batchsize.py

[CI] Add unit test framework (#1201)

2025-06-16 18:32:28 +08:00

test_fused_moe_allgather_ep.py

[CI] change to new ds model (#1513)

2025-06-30 19:02:29 +08:00

test_ilama_lora_tp2.py

[CI/UT] Unify model usage via ModelScope in CI (#1207)

2025-07-04 10:52:17 +08:00

test_offline_inference_distributed.py

Clean up v0.9.1 code (#1672)

2025-07-09 08:52:24 +08:00

test_prefix_caching.py

[CI/UT] Add test for chunk prefill and prefix cache on v1/AscendScheduler (#1505)

2025-07-02 16:57:03 +08:00

test_pyhccl_distributed.py

[CI] Add unit test framework (#1201)

2025-06-16 18:32:28 +08:00

test_torchair_graph_mode.py

[CORE]initial support for torchair with non-mla backend (#1506)

2025-07-03 22:21:42 +08:00