sychen52 fb21d8b4f9 Add NVFP4 MOE support for Deepseek V4. (#42209) ...

Signed-off-by: Shiyang Chen <shiychen@nvidia.com>

2026-05-22 07:21:51 -07:00

..

attention

[Experimental] Breakable CUDA graph (#42304)

2026-05-16 22:04:12 +08:00

fla

Update KDA chunk prefill decay to use exp2 semantics (#43195)

2026-05-21 01:16:27 -07:00

fused_moe

Add NVFP4 MOE support for Deepseek V4. (#42209)

2026-05-22 07:21:51 -07:00

mamba

[Attention] Mamba attention module refactor (#41126)

2026-05-22 17:13:12 +08:00

pooler

[Misc] Replace assert with proper exceptions for security and validation in pooling (#43286)

2026-05-22 18:43:33 +08:00

quantization

Add NVFP4 MOE support for Deepseek V4. (#42209)

2026-05-22 07:21:51 -07:00

rotary_embedding

Fix error in Dynamic NTK scaling (#41277)

2026-05-19 17:27:54 -04:00

__init__.py

Change the name to vLLM (#150)

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

activation.py

[Models][Gemma3/Gemma4] Support hidden_act variants in gated MLP (#40588)

2026-05-08 11:29:11 -07:00

attention_layer_base.py

[1/N][Attention] Restructure attention: move files (#31916)

2026-01-09 13:10:24 -08:00

batch_invariant.py

[Refactor] Cleanup batch invariant dead code (#41993)

2026-05-11 10:48:39 -04:00

conv.py

[Misc] Always use forward_mulmat for Conv3d on newer versions of torch. (#38487)

2026-03-30 05:39:41 +00:00

layernorm.py

[Aiter][ROCm] RMSNormGated+GroupedQuantFP8 fusion (#40710)

2026-05-14 15:37:09 -04:00

lightning_attn.py

[Bugfix] Use null block (0) for padded block table entries (#35431)

2026-03-30 14:02:51 -07:00

linear.py

[CPU] Add fused GDN support for AMX CPU platform (#42707)

2026-05-18 03:04:36 -07:00

logits_processor.py

[PluggableLayer][3/N] Apply PluggableLayer to llm_head and vocab embedding layer (#33465)

2026-04-10 16:12:59 +08:00

mhc.py

[ROCm] [Bugfix] Fix DeepSeek V4 Functionality and Accuracy (#42810)

2026-05-17 12:18:50 -04:00

mla.py

[Feature]: IndexCache support for DSA models (#37735)

2026-04-29 15:15:35 -04:00

resampler.py

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

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

sparse_attn_indexer.py

[XPU] Enable multiple key kernels for sparse attention (#37888)

2026-05-22 12:02:51 +08:00

utils.py

[CPU] Add fused GDN support for AMX CPU platform (#42707)

2026-05-18 03:04:36 -07:00

vocab_parallel_embedding.py

Bug/test eagle dp v0 (#38938)

2026-04-13 20:50:08 +00:00