xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-06-09 07:02:25 +08:00
Code Issues Packages Projects Releases Wiki Activity
6,600 Commits 155 Branches 89 Tags
Commit Graph

339 Commits

Author SHA1 Message Date
Michael Goin
f4a8a37465
[Minor] Rename quantization nvfp4 to modelopt_fp4 (#18356) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-05-20 09:08:37 -07:00
Random Fly
bca55b556f
[Bugfix] fix adding bias twice in ipex GPTQ quantization (#18363) 
Signed-off-by: rand-fly <randfly@outlook.com>
 2025-05-20 00:54:33 -07:00
Wenhua Cheng
e2ee1e8e9e
[Feature]Add support for models quantized with AutoRound (#17850) 
Signed-off-by: wenhuach21 <wenhua.cheng@intel.com>
 2025-05-19 09:38:53 -07:00
Lain
e23564cb70
use ceil_div in cutlass block scaling shape check (#17918) 2025-05-16 03:02:58 -07:00
Jerry Zhang
7974736740
Add support for loading torchao models with AOPerModuleConfig (#17826) 
Signed-off-by: Jerry Zhang <jerryzh168@gmail.com>
 2025-05-14 16:24:59 -07:00
bnellnm
f9c069c85e
Modularize fused experts and integrate PPLX kernels (#15956) 2025-05-14 13:11:54 -07:00
TJian
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
Michael Goin
9a2a6357de
[Bugfix] Fix FP8 Marlin MoE and enable for compressed-tensors models (#18026) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-05-13 19:48:33 -07:00
Pavani Majety
65f0f74b66
[Hardware/NVIDIA/Modelopt] Fix modelopt forward method for v1 torch.compile (#18101) 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
 2025-05-13 19:33:00 -07:00
vllmellm
40de1ef455
[FEAT] [ROCm]: Add AITER Block-Scaled GEMM Feature (#14968) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-05-13 19:08:20 -07:00
Harry Mellor
6223dd8114
Update deprecated type hinting in model_executor/layers (#18056) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-05-13 04:17:23 -07:00
Michael Goin
ea6ae8cb45
[Bugfix] Fix marlin moe fallback logic for llama4 (#18042) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-05-13 07:53:28 +00:00
Michael Goin
1df491c522
[Bugfix] Fixes for new marlin moe usage (#18017) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-05-13 03:50:04 +00:00
Michael Goin
307939f299
Use NVFP4 Marlin for CompressedTensorsW4A16Fp4 (#18000) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Dipika <dipikasikka1@gmail.com>
Co-authored-by: Dipika <dipikasikka1@gmail.com>
 2025-05-12 18:07:34 -06:00
Michael Goin
f065de4e88
Fix FBGEMM integration (#18002) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-05-12 23:02:07 +00:00
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