Skip to content

Commit 4f95f92

Browse files
authored
Update README.md (#2409)
1 parent 9ad7748 commit 4f95f92

1 file changed

Lines changed: 2 additions & 2 deletions

File tree

README.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@
2222
## Latest News
2323
* 02/09/2026 [5.7.0](https://github.com/ModelCloud/GPTQModel/releases/tag/v5.7.0): ✨New `MoE.Routing` config with `Bypass` and `Override` options to allow multiple brute-force MoE routing controls for higher quality quantization of MoE experts. Combined with `FailSafeStrategy`, GPT-QModel now has three separate control settings for efficient MoE expert quantization.
2424
`AWQ` `qcfg.zero_point` property has been merged with a unified `sym` symmetry property; `zero_point=True` is now `sym=False`.
25-
Fixed `AWQ` `sym=True` packing/inference and quantization compatibility with some Qwen3 models.
25+
Fixed `AWQ` `sym=True` packing/inference and quantization compatibility with some Qwen3 models. Exaone 4.0 support.
2626

2727
* 12/31/2025 5.7.0-dev: ✨New `FailSafe` config and `FailSafeStrategy`, auto-enabled by default, to address uneven routing of MoE experts resulting in quantization issues for some MoE modules. `Smooth` operations are introduced to `FailSafeStrategy` to reduce the impact of outliers in `FailSafe` quantization using `RTN` by default. Different `FailSafeStrategy` and `Smoothers` can be selected. `Threshold` to activate `FailSafe` can also be customized.
2828
New Voxtral and Glm-4v model support, plus audio dataset calibration for Qwen2-Omni. `AWQ` compatibility fix for `GLM 4.5-Air`.
@@ -183,7 +183,7 @@ GPT-QModel is a modular design supporting multiple quantization methods and feat
183183
## Model Support
184184
| Model | | | | | | | | | |
185185
|-------------------|---|---------------|---|----------------|---|----------------|---|---------------------|---|
186-
| Apertus || EXAONE 3.0 || Dots1 || Mistral3 || Qwen 2/3 (Next/MoE) ||
186+
| Apertus || EXAONE 3/4 || Dots1 || Mistral3 || Qwen 2/3 (Next/MoE) ||
187187
| Baichuan || Falcon (H1) || InternLM 1/2.5 || Mixtral || Qwen 2/2.5/3 VL ||
188188
| Bloom || FastVLM || Kimi K2 || MobileLLM || Qwen 2.5/3 Omni ||
189189
| ChatGLM || Gemma 1/2/3 || Klear || MOSS || RefinedWeb ||

0 commit comments

Comments
 (0)