Wentao Ye 86ed77022d [Feature] Batch Invariant for R1 TP 8 on Blackwell (#27229) ...

Signed-off-by: yewentao256 <zhyanwentao@126.com>

2025-10-21 10:25:55 -07:00

..

fla

[Kernel] Accelerate solve_tril with TMA (#26746)

2025-10-20 05:39:02 +00:00

fused_moe

[Bugfix] Fix gpt-oss w4a8 DP/EP on B200 (#26729)

2025-10-21 01:51:14 -04:00

mamba

[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

2025-10-18 09:48:22 -07:00

quantization

[ROCM] Enable CompressedTensorsWNA16 (#27187)

2025-10-21 10:43:23 -04:00

rotary_embedding

[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

2025-10-18 09:48:22 -07:00

__init__.py

Change the name to vLLM (#150)

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

activation.py

[Misc] Move utils to avoid conflicts with stdlib, and move tests (#27169)

2025-10-19 05:20:55 -07:00

attention_layer_base.py

[Misc] Refactor get_kv_cache_spec into AttentionLayerBase (#26587)

2025-10-18 13:51:21 +00:00

batch_invariant.py

[Feature] Batch Invariant for R1 TP 8 on Blackwell (#27229)

2025-10-21 10:25:55 -07:00

layernorm.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

2025-10-18 09:48:22 -07:00

lightning_attn.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

linear.py

[Minor] Remove unnecessary error message (#27115)

2025-10-17 20:02:12 +00:00

logits_processor.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

mla.py

Deepseek-v3 Batch Invariant on 8xH100 (#26609)

2025-10-15 22:06:02 -07:00

pooler.py

[Chore] Separate out vllm.utils.importlib (#27022)

2025-10-17 00:48:59 +00:00

resampler.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

utils.py

[cpu] Dispatch un-quantized linear to oneDNN/ACL by default for AArch64 (#27183)

2025-10-21 02:02:58 +00:00

vocab_parallel_embedding.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00