Commits · eb85f67d36ccd72e7cdf5cdc29954a265603e062 · OpenDAS / AutoAWQ

06 Apr, 2024 2 commits
- Add download_kwargs for load model (#302) (#399) · eb85f67d
  Roshiago authored Apr 06, 2024
  
  eb85f67d
- Implement `apply_clip` argument to `quantize()` (#427) · b5db7fcd
  Casper authored Apr 06, 2024
  
  b5db7fcd
11 Mar, 2024 1 commit
- Add Gemma Support (#393) · 94e73f0b
  TechxGenus authored Mar 11, 2024
  
  94e73f0b
24 Feb, 2024 1 commit
- New optimized kernels (#365) · 68c727a1
  Casper authored Feb 25, 2024
  
  68c727a1
16 Feb, 2024 1 commit
- Support Fused Mixtral on multi-GPU (#352) · 79b6fbd8
  Casper authored Feb 16, 2024
  
  79b6fbd8
15 Feb, 2024 1 commit

Casper authored Feb 15, 2024


Co-authored-by: jinz2014 <7799920+jinz2014@users.noreply.github.com>
Co-authored-by: Jin Z <5zj@cousteau.ftpn.ornl.gov>

bcaa8a36

03 Feb, 2024 3 commits
- Add qwen2 (#321) · cc75d0e8
  Junyang Lin authored Feb 03, 2024
  
  cc75d0e8
- Marlin symmetric quantization and inference (#320) · 34085edc
  Ilyas Moutawwakil authored Feb 03, 2024
```
Co-authored-by: Casper <casperbh.96@gmail.com>
```
  34085edc
- AMD ROCM Support (#315) · f018d2b7
  Ilyas Moutawwakil authored Feb 03, 2024
  
  f018d2b7
24 Jan, 2024 1 commit
- Torch only inference + any-device quantization (#319) · c6c7b065
  Casper authored Jan 24, 2024
  
  c6c7b065
21 Jan, 2024 1 commit
- Exllama kernels support (#313) · 2fcbf268
  Ilyas Moutawwakil authored Jan 21, 2024
```
Co-authored-by: Casper <casperbh.96@gmail.com>
```
  2fcbf268
07 Jan, 2024 1 commit
- GGUF compatible quantization (2, 3, 4 bit / any bit) (#285) · a3db8099
  Casper authored Jan 07, 2024
  
  a3db8099
23 Dec, 2023 2 commits
- Add Baichuan2 Support (#247) · cef9f113
  Aoyu authored Dec 23, 2023
```
Co-authored-by: Casper <casperbh.96@gmail.com>
```
  cef9f113
- FEAT: add llava to autoawq (#250) · 9e8e28b2
  Younes Belkada authored Dec 23, 2023
```
Co-authored-by: Casper <casperbh.96@gmail.com>
```
  9e8e28b2
22 Dec, 2023 2 commits
- Fused rope theta (#270) · 727172e9
  Casper authored Dec 23, 2023
```
Co-authored-by: Casper Hansen <casperbh96@gmail.com>
```
  727172e9
- Mixtral: Mixture of Experts quantization (#251) · 5b9f3c47
  Casper authored Dec 22, 2023
  
  5b9f3c47
11 Dec, 2023 1 commit
- FEAT: Add possibility of skipping modules when quantizing (#248) · 9c3dfa07
  Younes Belkada authored Dec 11, 2023
  
  9c3dfa07
08 Dec, 2023 2 commits
- Load on CPU to avoid OOM (#236) · 6b5dc29f
  Casper authored Dec 08, 2023
  
  6b5dc29f
- Fixed an issue where the Qwen model had too much error after quantization (#243) · 5eb1d2f0
  jundolc authored Dec 08, 2023
  
  5eb1d2f0
03 Dec, 2023 1 commit
- Pass `model_init_kwargs` to `check_and_get_model_type` function (#232) · 5a673bf8
  정한 Rycont authored Dec 03, 2023
  
  5a673bf8
28 Nov, 2023 1 commit
- New scaling to improve perplexity (#216) · d1112e1c
  Casper authored Nov 28, 2023
  
  d1112e1c
20 Nov, 2023 1 commit
- Add Qwen model (#182) · e440c7ac
  Qing authored Nov 20, 2023
```
Co-authored-by: Casper Hansen <casperbh.96@gmail.com>
```
  e440c7ac
18 Nov, 2023 2 commits
- Add config to Base model (#207) · 84c87877
  Casper authored Nov 18, 2023
  
  84c87877
- Fix MPT (#206) · 0e77dbc1
  Casper authored Nov 18, 2023
  
  0e77dbc1
15 Nov, 2023 1 commit
- [`core`] Replace `QuantLlamaMLP` with `QuantFusedMLP` (#188) · 3b362c0d
  Younes Belkada authored Nov 15, 2023
  
  3b362c0d
14 Nov, 2023 1 commit
- Fix multi-GPU loading and inference (#190) · 09c73fb2
  Casper authored Nov 14, 2023
  
  09c73fb2
11 Nov, 2023 1 commit
- Pass arguments to AutoConfig (#97) · 7c976752
  Andrey Glushenkov authored Nov 11, 2023
```
Co-authored-by: Casper <casperbh.96@gmail.com>
```
  7c976752
10 Nov, 2023 1 commit
- Make sure to delete dummy model (#180) · 1f6f5155
  Casper authored Nov 10, 2023
  
  1f6f5155
06 Nov, 2023 1 commit
- Yi support (#167) · 37c63440
  Casper authored Nov 06, 2023
  
  37c63440
04 Nov, 2023 2 commits
- Create fused LlamaLikeModel (#152) · 8110e028
  Casper authored Nov 04, 2023
  
  8110e028
- Default to safetensors for quantized models (#151) · 84a26861
  Casper authored Nov 04, 2023
  
  84a26861
31 Oct, 2023 1 commit
- AwqConfig class (#132) · eea08aa6
  Casper authored Oct 31, 2023
  
  eea08aa6
28 Oct, 2023 2 commits
- Support Aquila models. (#123) · dc13f0b8
  ldwang authored Oct 28, 2023
```
Signed-off-by: ldwang <ftgreat@gmail.com>
Co-authored-by: ldwang <ftgreat@gmail.com>
Co-authored-by: Casper Hansen <casperbh.96@gmail.com>
```
  dc13f0b8
- Fixing starcoder based models with 15B (#118) · 6c05f669
  Sebastian Bodza authored Oct 28, 2023
  
  6c05f669
19 Oct, 2023 1 commit
- add comments · bcfdeb38
  twaka authored Oct 17, 2023
  
  bcfdeb38
17 Oct, 2023 1 commit
- gpt_neox · ad45716f
  twaka authored Oct 17, 2023
  
  ad45716f
05 Oct, 2023 1 commit
- Remove warning · 661047f1
  Casper authored Oct 05, 2023
  
  661047f1
02 Oct, 2023 1 commit
- Mistral fused modules · d5bb4ec8
  Casper Hansen authored Oct 02, 2023
  
  d5bb4ec8
27 Sep, 2023 2 commits
- Add exception handling · 1ac3f976
  Casper Hansen authored Sep 27, 2023
  
  1ac3f976
- Mistral support · bd56c301
  Casper Hansen authored Sep 27, 2023
  
  bd56c301