GitLab

Auto CPU Offload in flux.py: add the auto option in the CPU offloading

Fix #162

This should fix mit-han-lab/nunchaku#162

Fix missing third_party & merge main branch of dev repo

This reverts commit 89cb1277.

[minor] add back the third party directory

Support 4-bit text encoder and per-layer CPU offloading, reducing FLUX's minimum memory requirement to just 4 GiB while maintaining a 2–3× speedup. Fix various issues related to resolution, LoRA, pin memory, and runtime stability. Check out the release notes for full details!

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>

Update Serialization.cpp

Used to resolve Windows 10 crash issues.

fix typo

Finalizing deepcompressor migration