Chengji Yao 8e882ffdc0

[Bugfix][TPU] fix moe custom kernel import (#18853) ...

Signed-off-by: Chengji Yao <chengjiyao@google.com>

2025-05-28 19:34:19 -07:00

..

fused_moe

[Bugfix][TPU] fix moe custom kernel import (#18853)

2025-05-28 19:34:19 -07:00

mamba

feat(rocm-support): support mamba2 on rocm (#18565)

2025-05-27 00:07:53 -07:00

quantization

[Neuron] Support quantization on neuron (#18283)

2025-05-27 22:10:33 +00:00

__init__.py

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00

activation.py

[New Model]: support GTE NewModel (#17986)

2025-05-14 01:31:31 -07:00

layernorm.py

Update deprecated type hinting in model_executor/layers (#18056)

2025-05-13 04:17:23 -07:00

lightning_attn.py

[Bugfix] Fix triton import with local TritonPlaceholder (#17446)

2025-05-06 17:53:09 +08:00

linear.py

[V1][Quantization] Add CUDA graph compatible v1 GGUF support (#18646)

2025-05-27 04:40:28 +00:00

logits_processor.py

[Misc] Slight spelling modification (#18039)

2025-05-12 20:36:27 -07:00

pooler.py

Prevent the cross-encoder logic from being applied to classification tasks (#18838)

2025-05-28 19:16:17 -07:00

rejection_sampler.py

Include private attributes in API documentation (#18614)

2025-05-23 06:18:31 -07:00

resampler.py

Update deprecated type hinting in model_executor/layers (#18056)

2025-05-13 04:17:23 -07:00

rotary_embedding.py

[New Model]: support GTE NewModel (#17986)

2025-05-14 01:31:31 -07:00

sampler.py

[Doc] Convert Sphinx directives ( {class}, {meth}, {attr}, ...) to MkDocs format for better documentation linking (#18663)

2025-05-27 01:44:20 -07:00

spec_decode_base_sampler.py

Update deprecated type hinting in model_executor/layers (#18056)

2025-05-13 04:17:23 -07:00

typical_acceptance_sampler.py

Include private attributes in API documentation (#18614)

2025-05-23 06:18:31 -07:00

utils.py

Update deprecated type hinting in model_executor/layers (#18056)

2025-05-13 04:17:23 -07:00

vocab_parallel_embedding.py

Update deprecated type hinting in model_executor/layers (#18056)

2025-05-13 04:17:23 -07:00