python/sglang/srt/models/llama_embedding.py · 56a724eba301159f09a6661dc085954544705c00 · zhaoyu6 / sglang · GitLab

Find file Blame History Permalink

[QUANT] Add GPTQModel Dynamic Quantization + `lm_head` Quantization (#3790) · 56a724eb
Qubitium-ModelCloud authored Mar 05, 2025
```
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
Co-authored-by: ZX-ModelCloud <zx@modelcloud.ai>
```
56a724eb

llama_embedding.py 3.18 KB