3 people 9a161307f5 [torch.compile][ROCm][V1] Enable attention output FP8 fusion for V1 attention backends (#19767) ...

Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

2025-09-10 13:59:55 -07:00

..

fla

[Kernels] Add Flash Linear Attention Kernels (#24518)

2025-09-10 00:04:41 +08:00

fused_moe

[Bugfix] Fix DeepEP config for DP4TP4 (#23619)

2025-09-10 10:37:56 -07:00

mamba

[Bugfix] fix modelopt exclude_modules name mapping (#24178)

2025-09-10 10:20:46 -07:00

quantization

[torch.compile][ROCm][V1] Enable attention output FP8 fusion for V1 attention backends (#19767)

2025-09-10 13:59:55 -07:00

rotary_embedding

[V0 deprecation] Deprecate V0 Neuron backend (#21159)

2025-09-06 16:15:18 -07:00

shared_fused_moe

[Kernels] Overlap shared experts with send/recv (#23273)

2025-09-03 12:35:18 -04:00

__init__.py

Change the name to vLLM (#150)

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

activation.py

[V0 deprecation] Deprecate V0 Neuron backend (#21159)

2025-09-06 16:15:18 -07:00

attention_layer_base.py

[Attention] Unify mamba and attention backend selection (#23171)

2025-08-25 09:09:36 +00:00

layernorm.py

[ROCm][Bugfix] Fix Aiter RMSNorm (#23412)

2025-09-10 21:08:03 +08:00

lightning_attn.py

[Docs] Fix warnings in mkdocs build (#23649)

2025-08-26 18:19:23 +00:00

linear.py

[Bugfix] Fix broken deepseek fp8 TP weights loading (#24367)

2025-09-06 09:23:12 -07:00

logits_processor.py

[Platform] Custom ops support for LMhead and LogitsProcessor (#23564)

2025-09-10 06:26:31 -07:00

mla.py

[Attention][Platform] Refactor MLA to support Custom Op (#23332)

2025-09-04 02:46:37 -07:00

pooler.py

[Model] Systematic support for fp32 head, pooling models part (#23810)

2025-09-09 07:29:50 -07:00

resampler.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

sampler.py

[Chore][V0 Deprecation] Move LogProb to a separate file (#24055)

2025-09-01 12:07:53 -07:00

utils.py

[CPU] Refactor CPU unquantized linear (#24150)

2025-09-04 14:28:45 +08:00

vocab_parallel_embedding.py

[Platform] Custom ops support for LMhead and LogitsProcessor (#23564)

2025-09-10 06:26:31 -07:00