vllmellm 5ebf66748b [FEAT][ROCm] Integrate Fused MoE Kernels from AITER (#14967) ...

Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>

2025-03-26 16:30:30 +08:00

..

decoder_only

[FEAT][ROCm] Integrate Fused MoE Kernels from AITER (#14967)

2025-03-26 16:30:30 +08:00

embedding

[Core] Update dtype detection and defaults (#14858)

2025-03-19 13:49:33 +08:00

encoder_decoder

Enable CUDA graph support for llama 3.2 vision (#14917)

2025-03-19 23:29:16 -07:00

fixtures

[Mistral-Small 3.1] Update docs and tests (#14977)

2025-03-18 03:29:42 -07:00

multimodal

[Misc] Clean up MiniCPM-V/O code (#15337)

2025-03-25 10:22:52 +00:00

__init__.py

[CI/Build] Move test_utils.py to tests/utils.py (#4425)

2024-05-13 23:50:09 +09:00

registry.py

[Model] Support Tele-FLM Model (#15023)

2025-03-22 02:04:44 -07:00

test_initialization.py

[V1] V1 Enablement Oracle (#13726)

2025-03-14 22:02:20 -07:00

test_oot_registration.py

[Bugfix][ROCm] running new process using spawn method for rocm in tests. (#14810)

2025-03-17 11:33:35 +00:00

test_registry.py

[Bugfix][ROCm] running new process using spawn method for rocm in tests. (#14810)

2025-03-17 11:33:35 +00:00

test_transformers.py

Transformers backend already supports V1 (#15463)

2025-03-25 20:26:16 -07:00

test_vision.py

[Bugfix] Fix Positive Feature Layers in Llava Models (#13514)

2025-02-19 08:50:07 +00:00

utils.py

[Core] Update dtype detection and defaults (#14858)

2025-03-19 13:49:33 +08:00