Shu Wang b2c8ce57c6 Fix Flashinfer CUTLASS MOE Allgather (#21963) ...

Signed-off-by: Shu Wang <shuw@nvidia.com>

2025-08-07 19:18:25 -07:00

..

fused_moe

Fix Flashinfer CUTLASS MOE Allgather (#21963)

2025-08-07 19:18:25 -07:00

mamba

[v1] - Mamba1 Attention Metadata (#21249)

2025-08-06 17:03:42 -07:00

quantization

Support Tensorrt-LLM MoE fp4 for low-latency (#21331)

2025-08-07 19:18:22 -07:00

rotary_embedding

[FEAT] Refactor ROPE into module (#22192)

2025-08-04 19:12:16 -07:00

__init__.py

Change the name to vLLM (#150)

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

activation.py

[CI/Build][Bugfix] Fix Qwen2.5 tests in CPU CI via fallback silu_and_mul to torch native implementation (#22145)

2025-08-03 05:34:04 -07:00

layernorm.py

[V0 deprecation] Remove V0 HPU backend (#21131)

2025-07-17 16:37:36 -07:00

lightning_attn.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

linear.py

[perf] Add fused MLA QKV + strided layernorm (#21116)

2025-07-22 07:07:44 -07:00

logits_processor.py

[Model] New model support for microsoft/Phi-4-mini-flash-reasoning (#20702)

2025-07-12 06:02:10 -07:00

pooler.py

[Model] Pooling model activation supports per request control by PoolingParams (#20538)

2025-08-05 00:37:00 -07:00

resampler.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

sampler.py

[V0 Deprecation] Remove V0 Spec Decode workers (#21152)

2025-07-18 21:47:50 -07:00

utils.py

[AMD][BugFix] Fix omission of wvSplitK kernel for small batch sizes (1-4) due to torch.compile (#21350)

2025-07-28 15:38:20 -04:00

vocab_parallel_embedding.py

[V0 deprecation] Remove V0 HPU backend (#21131)

2025-07-17 16:37:36 -07:00