ffb2cd6b54
[Perf] Optimize `moe_align_block_size` CUDA kernel ( #19572 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
2025-06-17 11:49:26 -07:00
ddfed314f9
Fixes IMA for TP w/ flex-attention ( #19712 )
...
Signed-off-by: drisspg <drisspguessous@gmail.com>
2025-06-17 04:01:50 +00:00
0b73736a0d
[Kernel] Raise verbose error and consolidate `num_heads/num_kv_heads` divisibility check ( #19339 )
...
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
2025-06-15 13:43:48 +08:00
b6efafd9e4
[Perf] Vectorize static / dynamic INT8 quant kernels ( #19233 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-06-12 06:51:41 -07:00
2f1c19b245
[CI] change spell checker from codespell to typos ( #18711 )
...
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2025-06-11 19:57:10 -07:00
29fa5cac1c
[Kernels] Add activation chunking logic to FusedMoEModularKernel ( #19168 )
...
Signed-off-by: Bill Nell <bnell@redhat.com>
2025-06-11 12:53:10 -04:00
7c644ab6d5
Fix Typo in Documentation and Function Name ( #19442 )
2025-06-10 22:44:11 -07:00
5f1ac1e1d1
Revert "[v1] Add fp32 support to v1 engine through flex attn" ( #19404 )
2025-06-10 01:30:20 -07:00
5cf2daea9a
[Misc] Fixes and Optimizations for DeepEP + DeepGEMM combination. ( #19298 )
...
Signed-off-by: Varun <vsundarr@redhat.com>
Co-authored-by: Varun <vsundarr@redhat.com>
2025-06-09 10:50:39 -04:00
b8089195b4
[v1] Add fp32 support to v1 engine through flex attn ( #19319 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-06-09 22:10:44 +08:00
cf02f9b283
Add FlexAttention to V1 ( #16078 )
...
Signed-off-by: drisspg <drisspguessous@gmail.com>
2025-06-06 21:58:55 -07:00
84166fee97
[Kernel] Integrate CUTLASS MoE kernel with PPLX ( #18762 )
...
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2025-06-06 18:26:11 -07:00
61059bee40
[Hardware][NVIDIA] FP4 MoE kernel optimization ( #19110 )
...
Signed-off-by: Chiyue Wei <chiyuew@nvidia.com>
Co-authored-by: Chiyue Wei <chiyuew@nvidia.com>
2025-06-05 09:48:26 -07:00
c3fd4d669a
[Kernel] Integrate batched/masked deepgemm kernel ( #19111 )
...
Signed-off-by: Varun <vsundarr@redhat.com>
Co-authored-by: Varun <vsundarr@redhat.com>
2025-06-04 21:59:18 +00:00
41aa578428
[NVIDIA] Add Cutlass MLA backend ( #17625 )
2025-06-03 21:40:26 -07:00
5d6d1adf15
[KERNEL] Sampler. CUDA kernel for applying repetition penalty ( #18437 )
2025-06-03 21:13:01 -07:00
4555143ea7
[CPU] V1 support for the CPU backend ( #16441 )
2025-06-03 18:43:01 -07:00
fa98d77773
[Kernel] DeepEP dispatch-combine kernel integration ( #18434 )
...
Signed-off-by: Varun <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
2025-06-03 12:30:02 -07:00
02f0c7b220
[Misc] Add SPDX-FileCopyrightText ( #19100 )
...
Signed-off-by: simon-mo <simon.mo@hey.com>
2025-06-03 11:20:17 -07:00
306d60401d
[ROCm][Kernel] Add gfx950 support for skinny gemms ( #18010 )
...
Signed-off-by: charlifu <charlifu@amd.com>
2025-05-31 07:40:05 -07:00
0f5e0d567e
[FEAT][ROCm] Add AITER grouped topk for DeepSeekV2 ( #18825 )
...
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
2025-05-31 03:39:31 -07:00
1aa2f81b43
[Misc] Update type annotation for rotary embedding `base` ( #18914 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-30 10:17:01 +08:00
269d901734
[Bugfix][ROCm] fix the power of 2 exception from triton_unified_attention.py when running llama4 models and unit test fix ( #18100 )
...
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-05-29 07:21:46 +08:00
1f1b1bc03b
[V1][Quantization] Add CUDA graph compatible v1 GGUF support ( #18646 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-05-27 04:40:28 +00:00
63934543a0
Speed up the `kernels/quantization/` tests ( #18669 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-05-25 05:02:59 +00:00
6e588da0f4
[Build/CI] Fix CUDA 11.8 build ( #17679 )
...
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-05-22 12:13:54 -07:00
dd5fa7e04f
[ROCm][Kernel][V1] Enable AMD Radeon GPU Custom Paged Attention on v1 ( #17004 )
...
Signed-off-by: Hosang Yoon <hosang.yoon@amd.com>
2025-05-21 08:35:00 -07:00
c6c10ca920
[Bugfix] Reduce moe_sum test size to avoid OOM ( #18484 )
...
Signed-off-by: Bill Nell <bnell@redhat.com>
2025-05-21 06:46:39 -07:00
92247c522e
[Bug] Fix moe_sum signature ( #18440 )
...
Signed-off-by: Bill Nell <bnell@redhat.com>
2025-05-20 22:37:08 -07:00
4e1c6a0264
[Bugfix] fix rotary embedding test for _get_padded_tensor_shape ( #18229 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-05-16 01:32:45 +00:00
e6b8e65d2d
[Bugfix] Fix fp8 tests for triton_unified_attention for Triton 3.3 ( #18013 )
...
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-05-15 13:26:34 +08:00
d93c976a0d
[Kernel] Have rotary embeddings support tensors ( #18046 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-05-14 15:43:55 -07:00
f9c069c85e
Modularize fused experts and integrate PPLX kernels ( #15956 )
2025-05-14 13:11:54 -07:00
612c2edb4f
[FEAT] [ROCm]: Add AITER CK 2 Stages MoE support ( #17110 )
...
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2025-05-14 03:03:11 -07:00
7b2f28deba
[AMD][torch.compile] Enable silu+fp8_quant fusion for rocm ( #18082 )
...
Signed-off-by: charlifu <charlifu@amd.com>
2025-05-13 22:13:56 -07:00
2d912fb66f
[FEAT] [ROCm] [V1]: Add AITER biased group topk for DeepSeekV3 ( #17955 )
...
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-05-13 22:03:47 -07:00
d74e5f37bc
[Kernel] fp4 marlin kernel ( #17687 )
...
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
2025-05-10 19:58:49 -07:00
246e3e0a36
fix broken test vllm:test_kernels - test_attention_selector.py::test_flash_attn ( #17873 )
...
Co-authored-by: Stephen Chen <tracelog@meta.com>
2025-05-10 10:46:54 +08:00
0c0fdae84f
[Hardware/NVIDIA/Kernel] Enable nvidia/DeepSeek-R1-FP4 Model ( #16362 )
2025-05-09 16:24:41 -07:00
6e5595ca39
[CI/Build] Automatically retry flaky tests ( #17856 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-09 09:55:17 -06:00
3c9396a64f
[FEAT][ROCm]: Support AITER MLA on V1 Engine ( #17523 )
...
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: qli88 <qiang.li2@amd.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
2025-05-09 10:42:05 +08:00
376786fac1
Add cutlass support for blackwell fp8 blockwise gemm ( #14383 )
...
Signed-off-by: Shu Wang <shuw@nvidia.com>
2025-05-08 15:09:55 -07:00
5a499e70d5
[Kernel][Hardware][AMD] Bf16 mfma opt for ROCm skinny GEMMs ( #17071 )
...
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: charlifu <charlifu@amd.com>
2025-05-07 22:34:49 -07:00
98c89e16ff
Make key optional for rotary embedding ( #17566 )
...
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
2025-05-07 00:11:46 -07:00
1a45a61387
[Kernel] GGUF MoeVec kernel ( #16780 )
...
Signed-off-by: SzymonOzog <szymon.ozog@aleph-alpha.com>
Signed-off-by: SzymonOzog <szymon.ozog@gmail.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
2025-05-06 23:07:23 -07:00
18dd5e01f2
[Model] Mamba2 causal conv1d Refactor to Split Prefill and Decode Requests for Corresponding Kernels ( #17146 )
...
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
2025-05-06 17:59:30 -07:00
2f925e5777
[Kernel] Unified Triton kernel that doesn't distinguish between prefill + decode ( #16828 )
...
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-05-06 18:21:48 -04:00
f9bc5a0693
[Bugfix] Fix triton import with local TritonPlaceholder ( #17446 )
...
Signed-off-by: Mengqing Cao <cmq0113@163.com>
2025-05-06 17:53:09 +08:00
6eae34533a
[Misc] Fix ScalarType float4 naming ( #17690 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-05-06 01:07:15 -07:00
1d0c9d6b2d
[Kernel] some optimizations for dense marlin and moe marlin ( #16850 )
...
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
2025-05-05 09:39:30 -07:00
Wentao Ye
Driss Guessous
22quinn
Ning Xie
bnellnm
leopardracer
Isotr0py
Varun Sundar Rabindranath
ElizaWszola
Chiyue Wei
Kaixi Hou
Vadim Gimpelson
Li, Jiang
Simon Mo
Charlie Fu
vllmellm
Cyrus Leung
Hongxia Yang
Michael Goin
Tyler Michael Smith
Hosang
Lucas Wilkinson
Thomas Parnell
TJian
Jinzhen Lin
tracelogfb
Pavani Majety
Shu Wang
Hashem Hashemi
Yong Hoon Shin
Szymon Ożóg
Chih-Chieh Yang
Mengqing Cao