boatman cdf027874c [Feat][OmniVoice]Support Varlen Attn, Request-Batch and Step-Execution (#6408) ...

Signed-off-by: boatman <109857087+sphinxkkkbc@users.noreply.github.com>

2026-09-08 18:58:38 -07:00

..

__init__.py

[Perf] [OmniVoice] Triton kernel fusion + CUDA Graph acceleration (#3336)

2026-05-22 13:12:47 +00:00

test_cuda_graph_generator.py

[Feat][OmniVoice]Support Varlen Attn, Request-Batch and Step-Execution (#6408)

2026-09-08 18:58:38 -07:00

test_decoder.py

[Perf] [OmniVoice] Triton kernel fusion + CUDA Graph acceleration (#3336)

2026-05-22 13:12:47 +00:00

test_fused_projection_load.py

[Feat][OmniVoice]Support Varlen Attn, Request-Batch and Step-Execution (#6408)

2026-09-08 18:58:38 -07:00

test_fused_qkv_rope.py

[Perf][Bugfix][OmniVoice] Restore float16 serving, and fuse the generator hot loop (#6317)

2026-09-02 19:54:55 +00:00

test_mask_dtype.py

[Feat][OmniVoice]Support Varlen Attn, Request-Batch and Step-Execution (#6408)

2026-09-08 18:58:38 -07:00

test_nonverbal_tags_tokenize.py

Add vLLM-Omni library info to Hugging Face Hub requests (#5381)

2026-09-08 10:08:38 -06:00

test_pipeline_batching.py

[Feat][OmniVoice]Support Varlen Attn, Request-Batch and Step-Execution (#6408)

2026-09-08 18:58:38 -07:00

test_triton_kernels.py

[Perf][Bugfix][OmniVoice] Restore float16 serving, and fuse the generator hot loop (#6317)

2026-09-02 19:54:55 +00:00