Commits · 85855252fd126635e70c1cf92f2d174660d31643 · fengzch-das / nunchaku

25 Apr, 2025 1 commit
- fix: fix the typo in FluxModel.cpp as in #297 (#317) · 85855252
  Muyang Li authored Apr 25, 2025
```
* fix: fix a typo

* style: format the imports
```
  85855252
23 Apr, 2025 1 commit
- fix: support for transformer block indices > 19 in forward_layer (FluxModel.cpp) (#308) · b87f4d3e
  shencuifeng authored Apr 23, 2025
```
* fix forward_layer in FluxModel.cpp

* Update FluxModel.cpp
```
  b87f4d3e
19 Apr, 2025 1 commit
- [major] fix error when device_id != 0 · 88b96b2a
  sxtyzhangzk authored Apr 17, 2025
  
  88b96b2a
08 Apr, 2025 1 commit
- Support batch inference in flux model · dbbd3ac8
  Zhekai Zhang authored Apr 08, 2025
  
  dbbd3ac8
04 Apr, 2025 3 commits
- Fix resolution issue in flashattn2 · 83b7542d
  sxtyzhangzk authored Apr 03, 2025
  
  83b7542d
- [major] fix runtime error when controlnet is not present · bf3669dd
  sxtyzhangzk authored Apr 02, 2025
  
  bf3669dd
- Add controlnet · 235238bd
  Hyunsung Lee authored Apr 02, 2025
  
  235238bd
01 Apr, 2025 12 commits
- fix shape in GEMM W8A8 · 63913f29
  LeeDongYeun authored Mar 28, 2025
  
  63913f29
- Flexible lora ranks · e05256c8
  sxtyzhangzk authored Apr 01, 2025
  
  e05256c8
- Fix the docker image; remove comfyui folder; · aece8f87
  Muyang Li authored Mar 29, 2025
  
  aece8f87
- Fix compile error on CUDA 12.4- · 60a0d6d7
  sxtyzhangzk authored Mar 27, 2025
  
  60a0d6d7
- [major] fix compilation error · fcc551cb
  sxtyzhangzk authored Mar 26, 2025
```
WHO THE HELL INVENTED ADL?
```
  fcc551cb
- [major] fix missing file · 9c92fe81
  sxtyzhangzk authored Mar 26, 2025
  
  9c92fe81
- Support Turing (sm_75) architecture · bf4adfeb
  sxtyzhangzk authored Mar 26, 2025
  
  bf4adfeb
- Add our own FP16 Attention implementation · 92ac7b40
  sxtyzhangzk authored Mar 22, 2025
  
  92ac7b40
- Add SanaModel caching · bf0813a6
  Hyunsung Lee authored Mar 18, 2025
  
  bf0813a6
- [major] add setDevice & load weights from pytorch · 27232e7b
  sxtyzhangzk authored Mar 10, 2025
  
  27232e7b
- [feat] add first block cache · 0b1891cd
  muyangli authored Mar 10, 2025
  
  0b1891cd
- Add dynamic Caching when batch_size = 1 for flux model · 39f90121
  Hyunsung Lee authored Mar 12, 2025
  
  39f90121
08 Mar, 2025 2 commits
- [major] checkError should clear cuda last error · df37484a
  sxtyzhangzk authored Mar 08, 2025
```
This should fix mit-han-lab/nunchaku#162
```
  df37484a
- [major] merge dev repo v0.1.4 · 75dad570
  Zhekai Zhang authored Mar 07, 2025
  
  75dad570
07 Mar, 2025 1 commit

muyangli authored Mar 07, 2025


Co-authored-by: Zhekai Zhang <sxtyzhangzk@gmail.com>
Co-authored-by: Muyang Li <lmxyy1999@foxmail.com>
Co-authored-by: Yujun Lin <16437040+synxlin@users.noreply.github.com>

873a35be

05 Mar, 2025 1 commit
- Update Serialization.cpp · e9618ab9
  PengXin authored Mar 06, 2025
```
Used to resolve Windows 10 crash issues.
```
  e9618ab9
27 Feb, 2025 1 commit
- Adding INT16 to ScalarType Tensor · 004e4e31
  Samuel Tesfai authored Feb 26, 2025
```
Finalizing deepcompressor migration
```
  004e4e31
22 Feb, 2025 2 commits
- [major] fix missing `apply_act` · d7896cb4
  sxtyzhangzk authored Feb 22, 2025
  
  d7896cb4
- [major] fix `load_act` missing · 68728d3a
  sxtyzhangzk authored Feb 22, 2025
  
  68728d3a
20 Feb, 2025 1 commit
- [major] support NVFP4; upgrade to 0.1 · 54e6d065
  muyangli authored Feb 20, 2025
  
  54e6d065
13 Feb, 2025 1 commit

Moving gemm kernels to awq · 91c7b53c

Samuel Tesfai authored Feb 13, 2025

Removing torch dependencies in gemm kernel
Merged tinychat_pybind and pybind
Merged the load and setup script

91c7b53c

11 Feb, 2025 1 commit
- [minor] update README · d57a18e1
  muyangli authored Feb 11, 2025
  
  d57a18e1
23 Jan, 2025 1 commit
- [major] support SANA · e9ad0535
  muyangli authored Jan 23, 2025
  
  e9ad0535
11 Nov, 2024 6 commits
- [major] workaround layout issue on gcc :( · 2f9b307c
  sxtyzhangzk authored Nov 10, 2024
  
  2f9b307c
- [major] fix running on Windows · e3e2a92a
  Zhekai Zhang authored Nov 10, 2024
  
  e3e2a92a
- [major] fix build on windows · 08204531
  sxtyzhangzk authored Nov 10, 2024
  
  08204531
- [major] fix build on windows · b1fec976
  sxtyzhangzk authored Nov 10, 2024
  
  b1fec976
- [major] move bf16 to compiler args; fp16 experiment · a9f1b7af
  sxtyzhangzk authored Nov 10, 2024
  
  a9f1b7af
- [major] fix build issue · d02f26df
  sxtyzhangzk authored Nov 10, 2024
  
  d02f26df
10 Nov, 2024 1 commit
- [major] alternative method to load safetensors · 0c1c2d4a
  sxtyzhangzk authored Nov 09, 2024
  
  0c1c2d4a
08 Nov, 2024 1 commit
- Initial release · 37c494a7
  Zhekai Zhang authored Nov 07, 2024
  
  37c494a7