Lehua Ding e591fc16ca [AsyncScheduling] Support ray backend for async scheduling ...

Signed-off-by: Lehua Ding <lehuading@tencent.com>

2025-12-24 16:52:30 +08:00

..

__init__.py

…

test_async_scheduling.py

[AsyncScheduling] Support ray backend for async scheduling

2025-12-24 16:52:30 +08:00

test_async_spec_decode.py

[Attention] Make seq_lens_cpu optional in CommonAttentionMetadata to enable true async spec-decode (#29624)

2025-12-09 17:18:10 -08:00

test_cascade_attention.py

…

test_context_length.py

[Bugfix] Fix validate model input for decoder models (#27099)

2025-11-13 10:18:47 -08:00

test_correctness_sliding_window.py

[CI][ROCm] Fix test_correctness_sliding_window (#29243)

2025-12-02 04:53:27 +00:00

test_kv_sharing_fast_prefill.py

[CI][ROCm][tests/v1/e2e] Fix multiprocessing launch for the test (#29123)

2025-12-02 20:46:10 +00:00

test_lora_with_spec_decode.py

[Misc] remove useless v1 env (#29164)

2025-11-21 01:41:20 -08:00

test_min_tokens.py

…

test_pooling_chunked_prefill.py

…

test_spec_decode.py

[ROCm][CI] Skip multi-GPU speculative decoding tests when insufficient GPUs available (#30527)

2025-12-12 03:54:56 +00:00