781096e385
Expert Parallelism (EP) Support for DeepSeek V2 ( #12583 )
2025-02-24 07:33:20 -08:00
558db8083c
[V1][Kernel] Refactor the prefix_prefill kernel so that the caller no longer has to pass in the context lengths ( #13095 )
2025-02-22 05:25:41 -08:00
e109e598c7
[NVIDIA] Support nvfp4 cutlass gemm ( #13571 )
2025-02-22 05:24:05 -08:00
288cc6c234
[Attention] MLA with chunked prefill ( #12639 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com >
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com >
Co-authored-by: Patrick Horn <patrick.horn@gmail.com >
Co-authored-by: simon-mo <xmo@berkeley.edu >
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com >
2025-02-21 15:30:12 -08:00
3809458456
[Bugfix] Fix invalid rotary embedding unit test ( #13431 )
...
Signed-off-by: Liangfu Chen <liangfc@amazon.com >
2025-02-18 11:52:03 +00:00
124776ebd5
[ci] skip failed tests for flashinfer ( #13352 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com >
2025-02-16 22:09:15 +08:00
dc0f7ccf8b
[BugFix] Enhance test_pos_encoding to support execution on multi-devices ( #13187 )
...
Signed-off-by: wchen61 <wchen61@foxmail.com >
2025-02-16 08:59:49 +00:00
c1e37bf71b
[Kernel][Bugfix] Refactor and Fix CUTLASS 2:4 Sparse Kernels ( #13198 )
...
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com >
2025-02-14 00:01:14 +00:00
4fc5c23bb6
[NVIDIA] Support nvfp4 quantization ( #12784 )
2025-02-12 19:51:51 -08:00
aff404571b
Add Bamba Model ( #10909 )
...
Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com >
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com >
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com >
2025-02-06 15:22:42 -08:00
85ac82d228
[Kernel] Make rotary_embedding ops more flexible with input shape ( #12777 )
2025-02-06 08:46:13 -08:00
75e94309e8
[Perf] Mem align KV caches for CUDA devices (MLA perf improvement) ( #12676 )
...
Signed-off-by: simon-mo <xmo@berkeley.edu >
Signed-off-by: Lucas Wilkinson <lcwilkins@redhat.com >
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com >
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com >
Co-authored-by: simon-mo <xmo@berkeley.edu >
2025-02-04 18:22:24 -08:00
c36ac98d01
[AMD][ROCm] Enable DeepSeek model on ROCm ( #12662 )
...
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com >
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com >
2025-02-04 08:24:11 +00:00
e489ad7a21
[Misc] Add SPDX-License-Identifier headers to python source files ( #12628 )
...
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com >
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com >
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com >
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com >
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com >
2025-02-02 11:58:18 -08:00
cabaf4eff3
[Attention] MLA decode optimizations ( #12528 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com >
Signed-off-by: simon-mo <xmo@berkeley.edu >
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu >
Co-authored-by: simon-mo <simon.mo@hey.com >
Co-authored-by: Michael Goin <mgoin64@gmail.com >
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com >
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com >
Co-authored-by: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com >
Co-authored-by: simon-mo <xmo@berkeley.edu >
2025-01-30 23:49:37 -08:00
9798b2fb00
[Kernel] Update cutlass_scaled_mm to support 2d group (blockwise) scaling ( #11868 )
2025-01-30 18:33:00 -08:00
27b78c73ca
[Kernel] add triton fused moe kernel for gptq/awq ( #12185 )
2025-01-29 09:07:09 -05:00
823ab79633
Update pre-commit hooks ( #12475 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2025-01-27 17:23:08 -07:00
2bc3fbba0c
[FlashInfer] Upgrade to 0.2.0 ( #11194 )
...
Signed-off-by: Bowen Wang <abmfy@icloud.com >
Signed-off-by: youkaichao <youkaichao@gmail.com >
Co-authored-by: youkaichao <youkaichao@gmail.com >
2025-01-27 18:19:24 +00:00
72f4880425
[Bugfix/CI] Fix broken kernels/test_mha.py ( #12450 )
2025-01-26 10:39:03 -08:00
aa2cd2c43d
[Bugfix] Disable w16a16 2of4 sparse CompressedTensors24 ( #12417 )
...
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com >
Co-authored-by: mgoin <michael@neuralmagic.com >
2025-01-26 19:59:58 +08:00
f1fc0510df
[Misc] Add FA2 support to ViT MHA layer ( #12355 )
...
Signed-off-by: Isotr0py <2037008807@qq.com >
2025-01-25 15:07:35 +08:00
ab5bbf5ae3
[Bugfix][Kernel] Fix CUDA 11.8 being broken by FA3 build ( #12375 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com >
2025-01-24 15:27:59 +00:00
e97f802b2d
[FP8][Kernel] Dynamic kv cache scaling factors computation ( #11906 )
...
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com >
Co-authored-by: Micah Williamson <micah.williamson@amd.com >
2025-01-23 18:04:03 +00:00
978b45f399
[Kernel] Flash Attention 3 Support ( #12093 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com >
2025-01-23 06:45:48 -08:00
68c4421b6d
[AMD][Quantization] Add TritonScaledMMLinearKernel since int8 is broken for AMD ( #12282 )
...
Signed-off-by: Randall Smith <Randall.Smith@amd.com >
2025-01-23 00:10:37 +00:00
dd7c9ad870
[Bugfix] Remove hardcoded head_size=256 for Deepseek v2 and v3 ( #12067 )
...
Signed-off-by: Isotr0py <2037008807@qq.com >
2025-01-16 10:11:54 +00:00
3adf0ffda8
[Platform] Do not raise error if _Backend is not found ( #12023 )
...
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com >
Signed-off-by: Mengqing Cao <cmq0113@163.com >
Co-authored-by: Mengqing Cao <cmq0113@163.com >
2025-01-15 10:14:15 +00:00
42f5e7c52a
[Kernel] Support MulAndSilu ( #11624 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com >
2025-01-15 02:29:53 +00:00
263a870ee1
[Hardware][TPU] workaround fix for MoE on TPU ( #11764 )
2025-01-12 10:53:51 -05:00
cf5f000d21
[torch.compile] Hide KV cache behind torch.compile boundary ( #11677 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com >
2025-01-10 13:14:42 +08:00
405eb8e396
[platform] Allow platform specify attention backend ( #11609 )
...
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com >
Signed-off-by: Mengqing Cao <cmq0113@163.com >
Co-authored-by: Mengqing Cao <cmq0113@163.com >
2025-01-09 21:46:50 +08:00
e20c92bb61
[Kernel] Move attn_type to Attention.__init__() ( #11690 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com >
2025-01-07 00:11:28 +08:00
73001445fb
[V1] Implement Cascade Attention ( #11635 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu >
2025-01-01 21:56:46 +09:00
b12e87f942
[platforms] enable platform plugins ( #11602 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com >
2024-12-30 20:24:45 +08:00
2072924d14
[Model] [Quantization] Support deepseek_v3 w8a8 fp8 block-wise quantization ( #11523 )
...
Signed-off-by: mgoin <michael@neuralmagic.com >
Signed-off-by: simon-mo <simon.mo@hey.com >
Signed-off-by: simon-mo <xmo@berkeley.edu >
Co-authored-by: simon-mo <simon.mo@hey.com >
Co-authored-by: simon-mo <xmo@berkeley.edu >
Co-authored-by: HandH1998 <1335248067@qq.com >
2024-12-26 15:33:30 -08:00
5a9da2e6e9
[Bugfix][Build/CI] Fix sparse CUTLASS compilation on CUDA [12.0, 12.2) ( #11311 )
...
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com >
2024-12-19 02:43:30 +00:00
60508ffda9
[Kernel]: Cutlass 2:4 Sparsity + FP8/Int8 Quant Support ( #10995 )
...
Co-authored-by: Faraz Shahsavan <faraz.shahsavan@gmail.com >
Co-authored-by: ilmarkov <markovilya197@gmail.com >
Co-authored-by: Rahul Tuli <rahul@neuralmagic.com >
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com >
2024-12-18 09:57:16 -05:00
30870b4f66
[torch.compile] Dynamic fp8 + rms_norm fusion ( #10906 )
...
Signed-off-by: luka <luka@neuralmagic.com >
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com >
2024-12-13 03:19:23 +00:00
78029b34ed
[BugFix][Kernel]: fix illegal memory access in causal_conv1d when conv_states is None ( #10928 )
...
Signed-off-by: xffxff <1247714429@qq.com >
2024-12-08 01:21:18 +08:00
073a4bd1c0
[Kernel] Use out arg in flash_attn_varlen_func ( #10811 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu >
2024-12-01 17:55:39 -08:00
c27df94e1f
[Bugfix] Fix chunked prefill with model dtype float32 on Turing Devices ( #9850 )
...
Signed-off-by: Wallas Santos <wallashss@ibm.com >
Co-authored-by: Michael Goin <michael@neuralmagic.com >
2024-11-25 12:23:32 -05:00
05d1f8c9c6
[misc] move functions to config.py ( #10624 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com >
2024-11-25 09:27:30 +00:00
eebad39f26
[torch.compile] support all attention backends ( #10558 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com >
2024-11-22 14:04:42 -08:00
d200972e7f
[Bugfix] Marlin 2:4 temp fix for large M dim (>256) ( #10464 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com >
2024-11-19 19:40:33 -08:00
b00b33d77e
[Model][Quantization] HQQ support through Marlin kernel expansion ( #9766 )
...
Signed-off-by: ElizaWszola <eliza@neuralmagic.com >
2024-11-19 13:31:12 -08:00
8c1fb50705
[Platform][Refactor] Extract func get_default_attn_backend to Platform ( #10358 )
...
Signed-off-by: Mengqing Cao <cmq0113@163.com >
2024-11-19 11:22:26 +08:00
96d999fbe8
[Kernel] Initial Machete W4A8 support + Refactors ( #9855 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com >
2024-11-18 12:59:29 -07:00
79ee45b428
[Misc] Bump up test_fused_moe tolerance ( #10364 )
...
Signed-off-by: ElizaWszola <eliza@neuralmagic.com >
2024-11-15 16:31:18 +00:00
bf2ddc6610
[bugfix] Fix static asymmetric quantization case ( #10334 )
...
Signed-off-by: Daniël de Kok <me@danieldk.eu >
Signed-off-by: luka <luka@neuralmagic.com >
Co-authored-by: Daniël de Kok <me@danieldk.eu >
2024-11-15 09:35:11 +08:00
