anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Quantization] Redo Z-Image text encoder FP8 online quantization (#3279)

Browse Source 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
This commit is contained in:
Isotr0pyHongsheng LiuSYLAR
 authored and GitHub committed 2026-05-06 16:37:36 +00:00
1 parent b8bd75837e
commit 0a8204cb81
5 files changed
+191 -36
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/quantization/fp8.md
+9 -9
View File
@@ -32,15 +32,15 @@ guide. FP8 on Ampere may use a weight-only path where available.
### Diffusion Model (Qwen-Image, Wan2.2)
| Model | HF models | Online | Pre-calibrated | Recommendation | `ignored_layers` |
|-------|-----------|:-------:|:------:|----------------|------------------|
| Qwen-Image | `Qwen/Qwen-Image`, `Qwen/Qwen-Image-2512` | Yes | Yes | Skip sensitive image-stream MLPs when quality regresses | `img_mlp` |
| Wan2.2 | Wan2.2 diffusion pipelines | Not validated | Not validated | Validate against BF16 before documenting as supported | TBD |
| Z-Image | `Tongyi-MAI/Z-Image-Turbo` | Yes | Yes | All layers | None |
| FLUX.1 | `black-forest-labs/FLUX.1-dev`, `black-forest-labs/FLUX.1-schnell` | Yes | Yes | All layers | None |
| FLUX.2-klein | `black-forest-labs/FLUX.2-klein-4B` | Yes | Yes | All layers | None |
| HunyuanImage-3.0 | `tencent/HunyuanImage-3.0`, `tencent/HunyuanImage-3.0-Instruct` | Yes | Yes | All layers; use the Hunyuan stage config for multi-stage runs | None |
| HunyuanVideo-1.5 | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v`, `720p_t2v`, `480p_i2v` | Yes | Yes | All layers | None |
| Model | HF models | Online | Pre-calibrated | Recommendation | `ignored_layers` | Text-Encoder quantization |
|-------|-----------|:-------:|:------:|----------------|------------------|------------------|
| Qwen-Image | `Qwen/Qwen-Image`, `Qwen/Qwen-Image-2512` | Yes | Yes | Skip sensitive image-stream MLPs when quality regresses | `img_mlp` | |
| Wan2.2 | Wan2.2 diffusion pipelines | Not validated | Not validated | Validate against BF16 before documenting as supported | TBD | |
| Z-Image | `Tongyi-MAI/Z-Image-Turbo` | Yes | Yes | All layers | None | ✅︎ |
| FLUX.1 | `black-forest-labs/FLUX.1-dev`, `black-forest-labs/FLUX.1-schnell` | Yes | Yes | All layers | None | |
| FLUX.2-klein | `black-forest-labs/FLUX.2-klein-4B` | Yes | Yes | All layers | None | |
| HunyuanImage-3.0 | `tencent/HunyuanImage-3.0`, `tencent/HunyuanImage-3.0-Instruct` | Yes | Yes | All layers; use the Hunyuan stage config for multi-stage runs | None | |
| HunyuanVideo-1.5 | `hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v`, `720p_t2v`, `480p_i2v` | Yes | Yes | All layers | None | |
### Multi-Stage Omni/TTS Model (Qwen3-Omni, Qwen3-TTS)