3 people 94e9ef0768 [Bugfix] Don't transpose fused MoE quantization scales in RoutedExperts.load_weights (#50137) ...

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-07-31 08:46:52 -07:00

..

attention

[2/N][Attention] Enable masked MHA for sparse MLA prefills (#48770)

2026-07-31 06:01:24 -07:00

fused_moe

[Bugfix] Don't transpose fused MoE quantization scales in RoutedExperts.load_weights (#50137)

2026-07-31 08:46:52 -07:00

fusion

Fix docs build on main (#45536)

2026-06-13 08:53:23 -07:00

hpc

[Attention Backend] HPC_ATTN backend support mtp and dynamic scheduled attention (#47433)

2026-07-05 18:18:25 -07:00

mamba

[ROCm] Add tuned selective_state_update float16 config for AMD Instinct MI325X (#50006)

2026-07-31 02:43:53 +00:00

minimax_rms_norm

[ROCm][MiniMax-M2] Dispatch fused QK-norm + AllReduce via AITER (#44849)

2026-07-14 03:10:16 +00:00

pooler

[Core] Ensure memory is pinned prior to async h2d copy (#45424)

2026-06-20 20:02:24 -07:00

quantization

[ROCm][CI] Fall back to lossless Kimi K3 MXFP4 emulation on gfx942 (#50516)

2026-07-31 11:33:16 -04:00

rotary_embedding

[ROCm] Fix and optimize GPT-J-style MRoPE (#49906)

2026-07-28 10:50:10 -06:00

__init__.py

Change the name to vLLM (#150)

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

activation.py

[torch.compile] Compile CustomOp.forward_native for ReLU^2 to avoid raw torch ops inside opaque custom ops (#50244)

2026-07-29 18:27:31 +00:00

attention_layer_base.py

[3/N][KV-Cache Layout Refactor] Standardize Mamba cache; drop get_transfer_cache_regions (#44456)

2026-07-21 09:16:15 +00:00

batch_invariant.py

[BugFix] Don't apply weight in batch-invariant RMSNorm when has_weight=False (#48741)

2026-07-16 11:59:03 +08:00

conv.py

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

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

fused_allreduce_gemma_rms_norm.py

[Bugfix] Re-land MiniMax M3 default video processor (#50305)

2026-07-31 07:46:18 +00:00

fused_qk_norm_rope.py

[Perf] fuse qk rmsnorm rope gate for qwen3.5 (#44176)

2026-06-09 22:12:17 +08:00

layernorm.py

[Refactor] Move fla to third party (#48500)

2026-07-16 19:22:36 +01:00

lightning_attn.py

[Kernel][Test] Extend lightning_attn and awq_triton kernel tests to XPU (#43307)

2026-06-04 14:25:59 -04:00

linear.py

[CompressedTensors] FP4 Qutlass Integration (#43229)

2026-07-28 20:34:20 -06:00

logits_processor.py

[Spec Decode][Perf] Replicate DSpark Markov head across TP ranks (#49731)

2026-07-29 11:43:51 -04:00

mhc.py

[XPU]add sycl path for Mhc (#47245)

2026-07-20 15:32:54 +00:00

mla.py

[New model] Kimi K3 (#50000)

2026-07-30 03:49:58 -07:00

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

[Attention] Skip sparse indexer scoring for dense short prefills (#48407)

2026-07-28 16:17:22 +00:00

utils.py

Enable gfx1250 ROCm architecture (#46516)

2026-07-31 01:41:12 +00:00

vocab_parallel_embedding.py

[Spec Decode][Perf] Replicate DSpark Markov head across TP ranks (#49731)

2026-07-29 11:43:51 -04:00