GitLab

Enable 720p model inference on low-spec GPUs/CPUs and accelerate T5/CLIP quantized models with vLLM operators

* reconstruct quantization and fix memory leak bug.

* Support lazy load inference.

* reconstruct quantization

* Fix hunyuan bugs

* deleted tmp file

---------
Co-authored-by: root <root@pt-c0b333b3a1834e81a0d4d5f412c6ffa1-worker-0.pt-c0b333b3a1834e81a0d4d5f412c6ffa1.ns-devsft-3460edd0.svc.cluster.local>
Co-authored-by: gushiqiao <gushqiaio@sensetime.com>
Co-authored-by: gushiqiao <gushiqiao@sensetime.com>

* async offload & context4debug

* offload ratio

* Merge branch 'main' into xinchi/fix_offload

* adding offload ratio

* pre-commit

---------
Co-authored-by: “de1star” <“843414674@qq.com”>

* fix offload

* fix offload

---------
Co-authored-by: “de1star” <“843414674@qq.com”>

* [minor]: optimize dockerfile for fewer layer

* [feature]: add pre-commit lint, update readme for contribution guidance

* [minor]: fix run shell privileges

* [auto]: first lint without rule F, fix rule E

* [minor]: fix docker file error

* 修改了main.py, t5的model, wan的model、三个weights文件和三个infer文件, 并且在common的conv3d算子中注册新算子

* 修改了Conv3dWeightForceBF16算子，更新了wan的pre_weights中对此算子的使用

* 修复了import中的bug

* 修复了WanPreWeights, WanTransformerWeights没有self.config的bug

* 修复了WanPreWeights, WanTransformerWeights没有self.config的bug

* 修复了config的bug，目前在使用cpu_offload的时候，vae阶段有tensor不在同一device的bug

* 修复了vae阶段迁移的bug

* 修复了scale在mean和inv_std迁移后仍需重新赋值的bug