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

[AutoRound] Support WAN2.2 W4A16 quantization model (#3353)

Browse Source 
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Signed-off-by: hyh_hh <huyinghong1@huawei.com>
Co-authored-by: hxhhhlalala <hyh_hh@163.com>
Co-authored-by: hyh_hh <huyinghong1@huawei.com>
This commit is contained in:
Liang Lvhxhhhlalalahyh_hh
 authored and GitHub committed 2026-05-21 17:54:41 +08:00
1 parent 474710dda9
commit 8297570c2b
9 files changed
+680 -8
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/quantization/autoround.md
+3 -1
View File
@@ -32,7 +32,9 @@ guide. AutoRound is Intel-supported.
|-------|------------|-------|--------|---------|
| FLUX.1-dev | `vllm-project-org/FLUX.1-dev-AutoRound-w4a16` | Diffusion transformer | W4A16 | GPTQ-Marlin or Intel-supported AutoRound backend |
| Qwen-Image | Not listed | Diffusion transformer | W4A16 | Not validated |
| Wan2.2 | Not listed | Diffusion transformer | W4A16 | Not validated |
| Wan2.2-I2V | `Intel/Wan2.2-I2V-A14B-Diffusers-int4-AutoRound` | Diffusion transformer | W4A16 | GPTQ-Marlin or Intel-supported AutoRound backend |
| Wan2.2-T2V | `Intel/Wan2.2-T2V-A14B-Diffusers-int4-AutoRound` | Diffusion transformer | W4A16 | GPTQ-Marlin or Intel-supported AutoRound backend |
| Wan2.2-TI2V | `Intel/Wan2.2-TI2V-5B-Diffusers-int4-AutoRound` | Diffusion transformer | W4A16 | GPTQ-Marlin or Intel-supported AutoRound backend |
### Multi-Stage Omni/TTS Model (Qwen3-Omni, Qwen3-TTS)
docs/user_guide/quantization/mxfp4.md
+1 -1
View File
@@ -397,7 +397,7 @@ names** discovered in Step 1. No code changes to the model are required.
```python
omni = Omni(
model="/path/to/your-model",
quantization_config={
quantization={
"method": "mxfp4_dualscale",
"ignored_layers": [
"blocks.0.attn1.to_qkv", # runtime name, not diffusers name