3 people d6e04f4c43 [Bugfix] Cap FULL decode cudagraph sizes for Mamba/hybrid models (#34094) (#34571) ...

Signed-off-by: haosdent <haosdent@gmail.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>

2026-03-04 11:56:22 +01:00

..

__init__.py

[V1] Adding min tokens/repetition/presence/frequence penalties to V1 sampler (#10681)

2024-12-26 19:02:58 +09:00

test_gpu_input_batch.py

[Chore] Separate out vllm.utils.platform_utils.py (#27374)

2025-10-23 19:08:06 +00:00

test_gpu_model_runner.py

[Bugfix] Cap FULL decode cudagraph sizes for Mamba/hybrid models (#34094) (#34571)

2026-03-04 11:56:22 +01:00

test_gpu_profiler.py

Support custom URI schemes and trace handlers for profiler (#32393)

2026-01-22 09:45:40 -08:00

test_mamba_utils.py

[perf] Use pinned memory for async H2D transfer in do_mamba_copy_block (#35480)

2026-02-28 01:50:37 +08:00

test_utils.py

[5/N][Attention] Finish eliminating vllm/attention folder (#32064)

2026-01-27 10:02:51 -05:00

test_worker_memory_snapshot.py

[1/N] Elastic EP Milestone 2 (#34861)

2026-02-28 04:46:42 +00:00