Logo
Explore Help
Sign In
Public/automatic
1
0
Fork 0
You've already forked automatic
mirror of https://github.com/vladmandic/automatic synced 2026-08-27 23:51:00 +02:00
Code Issues Packages Projects Releases Wiki Activity
Files
17c8fe91e2579d393a44510d97eb8e15c1663c2d
automatic/modules/sdnq
T
History
Disty0 e1ac9650b7 Make SDNQ Triton kernels trigger way less tuning and fix accuracy issues on SDNQ Atten
2026-07-01 17:31:57 +03:00
..
kernels
Make SDNQ Triton kernels trigger way less tuning and fix accuracy issues on SDNQ Atten
2026-07-01 17:31:57 +03:00
layers
SDQN add OpenVINO FP16 MM and add update_torch_dtype to SDNQQuantizer
2026-06-20 21:41:34 +03:00
packed_int
lint
2026-06-02 17:13:08 +02:00
__init__.py
Refactor SDNQ quantizer handling and add modules_to_not_use_matmul
2026-05-15 05:47:32 +03:00
common.py
assume fp16 instead
2026-06-20 23:06:25 +03:00
dequantizer.py
fix asym quant with hadamard
2026-05-21 17:22:45 +03:00
file_loader.py
full codespell coverage
2026-06-04 12:36:10 +02:00
forward.py
SDNQ add nn.Embedding quantization support and add Gemma4 keys
2026-04-10 18:46:58 +03:00
loader.py
SDNQ show a warining for no Triton instead and stop overriding matmul to false
2026-06-17 02:17:21 +03:00
packed_float.py
SDNQ add 15, 13, 11 and 9 bit support
2026-03-11 03:39:02 +03:00
quant_utils.py
reduce warp range
2026-06-24 13:23:00 +03:00
quantizer.py
cleanup seedvr
2026-06-23 13:55:47 +02:00
utils.py
SDNQ add Hadamard Rotation support
2026-05-18 17:06:11 +03:00
Powered by Gitea Version: 1.26.4 Page: 242ms Template: 5ms
Auto
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API