biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
9,459 Commits 2 Branches 140 Tags
4979eb79da80a6dd7d4e52103053bf00b80c65cb
Commit Graph

524 Commits

Author SHA1 Message Date
Dipika Sikka
cd3edfc908 [Misc] Add compressed-tensors NVFP4A16 emulation support (#17914) 
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Signed-off-by: Dipika <dipikasikka1@gmail.com>
 2025-05-11 15:58:38 +08:00
Jinzhen Lin
d74e5f37bc [Kernel] fp4 marlin kernel (#17687) 
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
 2025-05-10 19:58:49 -07:00
Pavani Majety
0c0fdae84f [Hardware/NVIDIA/Kernel] Enable nvidia/DeepSeek-R1-FP4 Model (#16362) 2025-05-09 16:24:41 -07:00
Michael Goin
22481fbfa3 Update CT WNA16MarlinMoE integration (#16666) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-05-09 13:19:45 -04:00
Shu Wang
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
Michael Goin
4f605a6de5 Fix noisy warning for uncalibrated q_scale/p_scale (#17414) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-05-08 15:56:59 -04:00
fxmarty-amd
bb239a730f [Bugfix] Fix quark fp8 format loading on AMD GPUs (#12612) 
Signed-off-by: Felix Marty <felmarty@amd.com>
Signed-off-by: kewang2 <kewang2@amd.com>
Co-authored-by: kewang2 <kewang2@amd.com>
 2025-05-08 02:53:53 -07:00
Bowen Bao
db593aa67f [Quantization] Quark MXFP4 format loading (#16943) 2025-05-07 15:05:05 -04:00
Szymon Ożóg
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
Mengqing Cao
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
Jinzhen Lin
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
rasmith
e3d0a1d190 [Quantizaton] [AMD] Add support for running DeepSeek int8 w8a8 MoE on ROCm (#17558) 
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
 2025-05-02 21:41:10 -07:00
Eric Hartford
9b103a1d76 fix typo in logging (#17605) 2025-05-02 18:04:40 -07:00
Michael Goin
868c546da4 Support W8A8 INT8 MoE for compressed-tensors (#16745) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-05-02 10:03:32 -04:00
Michael Goin
b4003d11fc Check if bitblas is installed during support check (#17572) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-05-02 04:32:54 +00:00
Michael Goin
24aebae177 [Bugfix] Disable gptq_bitblas for <SM80 to fix GPTQ on V100/T4 (#17541) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-05-01 17:59:35 -07:00
NaLan ZeYu
1144a8efe7 [Bugfix] Temporarily disable gptq_bitblas on ROCm (#17411) 
Signed-off-by: Yan Cangang <nalanzeyu@gmail.com>
 2025-04-30 19:51:45 -07:00
Aaron Pham
da4e7687b5 [Fix] Support passing args to logger (#17425) 
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
 2025-04-30 08:06:58 -07:00
Harry Mellor
13698db634 Improve configs - ModelConfig (#17130) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-04-30 10:38:22 +08:00
a2q1p
0ed27ef66c Fix: Spelling of inference (#17387) 2025-04-29 09:23:39 -07:00
Charlie Fu
ed2462030f [Bugfix] Fix moe weight losing all extra attrs after process_weights_after_loading. (#16854) 
Signed-off-by: charlifu <charlifu@amd.com>
 2025-04-28 21:05:07 +00:00
Harry Mellor
c7941cca18 Explicitly explain quant method override ordering and ensure all overrides are ordered (#17256) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-04-28 16:55:31 +00:00
Harry Mellor
b6dd32aa07 Make name of compressed-tensors quant method consistent across vLLM (#17255) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-04-28 16:28:13 +00:00
Charlie Fu
54271bb766 [ROCm][Misc] Follow-ups for Skinny Gemms on ROCm. (#17011) 
Signed-off-by: charlifu <charlifu@amd.com>
 2025-04-25 22:05:10 -07:00
rasmith
68af5f6c5c [AMD][FP8][BugFix] Remove V1 check in arg_utils.py for FP8 since it is not necessary (#17215) 
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
 2025-04-25 19:55:05 -07:00
rasmith
a41351f363 [Quantization][FP8] Add support for FP8 models with input_scale for output projection and QK quantization (#15734) 
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
 2025-04-25 00:45:02 -07:00
vllmellm
eef364723c [FEAT] [ROCm]: AITER Fused MOE V1 Support (#16752) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-04-25 11:06:50 +08:00
Lei Wang
8d32dc603d [Kernel] Support Microsoft Runtime Kernel Lib for our Low Precision Computation - BitBLAS (#6036) 
Signed-off-by: xinyuxiao <xinyuxiao2024@gmail.com>
Co-authored-by: xinyuxiao <xinyuxiao2024@gmail.com>
 2025-04-22 09:01:36 +01:00
Charlie Fu
188b7f9b8c [Performance][ROCm] Add skinny gemms for unquantized linear on ROCm (#15830) 
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
 2025-04-21 20:46:22 -07:00
Varun Sundar Rabindranath
7b8a2ab76f [Kernel] Add expert_map support to Cutlass FP8 MOE (#16861) 
Signed-off-by: varun sundar rabindranath <vsundarr@redhat.com>
Co-authored-by: varun sundar rabindranath <vsundarr@redhat.com>
 2025-04-21 20:44:32 -07:00
kliuae
5b794cae8d [ROCm] Add aiter tkw1 kernel for Llama4 fp8 (#16727) 
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-04-21 20:42:34 -07:00
Dipika Sikka
54a66e5fee [Misc] Update compressed-tensors WNA16 to support zero-points (#14211) 2025-04-15 07:33:51 -06:00
Jinzhen Lin
d06ba4ed3f [Kernel] moe wna16 marlin kernel (#14447) 
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-04-14 20:05:22 -07:00
Michael Goin
d085a44082 Enable PTPC FP8 for CompressedTensorsW8A8Fp8MoEMethod (triton fused_moe) (#16537) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-04-13 14:55:18 +00:00
Michael Goin
f41647ee6b [Kernel] Support W8A8 channel-wise weights and per-token activations in triton fused_moe_kernel (#16366) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-04-11 17:54:08 +00:00
chaow-amd
9e90c9f73f [Bugfix] Fix bugs of running Quark quantized models (#16236) 
Signed-off-by: chaow <chaow@amd.com>
 2025-04-11 10:18:32 -04:00
Michael Goin
c70cf0fe06 [Kernel] Use moe_wna16 kernel for compressed tensors wna16 moe models (#16038) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-04-10 15:08:47 +08:00
yihong
04149cce27 [BugFix] fix some typos found by typos. (#16314) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2025-04-09 03:43:59 -07:00
Isotr0py
40b4284fe3 [Bugfix] Handle process_weights_after_loading for QKVCrossParallelLinear (#15328) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-04-08 10:02:23 -07:00
Michael Goin
21802c4b6d [ROCm][Bugfix][FP8] Make fp8 quant respect fused modules mapping (#16031) 
Signed-off-by: mgoin <michael@neuralmagic.com>
 2025-04-07 21:28:14 -04:00
Driss Guessous
652907b354 Torchao (#14231) 
Signed-off-by: drisspg <drisspguessous@gmail.com>
 2025-04-07 19:39:28 -04:00
Lu Fang
55dcce91df Upstream Llama4 Support to Main (#16113) 
Signed-off-by: Aston Zhang <22279212+astonzhang@users.noreply.github.com>
Signed-off-by: Chris Thi <chris.c.thi@gmail.com>
Signed-off-by: drisspg <drisspguessous@gmail.com>
Signed-off-by: Jon Swenson <jmswen@gmail.com>
Signed-off-by: Keyun Tong <tongkeyun@gmail.com>
Signed-off-by: Lu Fang <fanglu@meta.com>
Signed-off-by: Xiaodong Wang <xdwang@meta.com>
Signed-off-by: Yang Chen <yangche@fb.com>
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
Signed-off-by: Zijing Liu <liuzijing2014@gmail.com>
Signed-off-by: Lu Fang <lufang@fb.com>
Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: Lucia Fang <fanglu@fb.com>
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Lu Fang <fanglu@fb.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-04-07 08:06:27 -07:00
Jinzhen Lin
2fa66ef713 [Bugfix] fix use_atomic_add support of marlin kernel when using v1 engine (#15946) 
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
 2025-04-05 20:04:22 -07:00
LukasBluebaum
90969fb39a [Kernel] Add more dtype support for GGUF dequantization (#15879) 
Signed-off-by: lukas.bluebaum <lukas.bluebaum@aleph-alpha.com>
 2025-04-02 01:58:48 -07:00
bnellnm
e59ca942f5 Add option to use DeepGemm contiguous grouped gemm kernel for fused MoE operations. (#13932) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-04-01 12:07:43 -04:00
TJian
4965ec42d2 [FEAT] [ROCm] Add AITER int8 scaled gemm kernel (#15433) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-03-29 03:33:56 -07:00
Nicolò Lucchesi
da461f3cbf [TPU][V1][Bugfix] Fix w8a8 recompiilation with GSM8K (#15714) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-03-28 21:13:06 -07:00
Gregory Shtrasberg
4d0ec37267 [Quantization][FP8] Adding support for fp8 gemm layer input in fp8 (#14578) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2025-03-28 02:58:16 +00:00
Jee Jee Li
726efc6a32 [Quantization][V1] BitsAndBytes support V1 (#15611) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-03-28 10:12:47 +08:00
Robert Shaw
43ed4143c4 [Quantization] Fp8 Channelwise Dynamic Per Token GroupedGEMM (#15587) 
Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
Co-authored-by: Lucas Wilkinson <wilkinson.lucas@gmail.com>
Co-authored-by: ElizaWszola <ewszola@redhat.com>
 2025-03-27 06:47:25 +00:00