text-generation-webui/docs/What Works.md
oobabooga 2f08dce7b0 Remove ExLlamaV2 backend
- archived upstream: 7dc12af3a8
- replaced by ExLlamaV3, which has much better quantization accuracy
2026-03-05 14:02:13 -08:00

18 lines
797 B
Markdown

## What Works
| Loader | Loading LoRAs | Training LoRAs | Multimodal | Perplexity evaluation |
|----------------|---------------|----------------|------------|-----------------------|
| llama.cpp | ❌ | ❌ | ✅\* | ❌ |
| Transformers | ✅ | ✅ | ✅\*\* | ✅ |
| ExLlamav3_HF | ❌ | ❌ | ❌ | ✅ |
| ExLlamav3 | ❌ | ❌ | ✅ | ❌ |
| TensorRT-LLM | ❌ | ❌ | ❌ | ❌ |
❌ = not supported
✅ = supported
\* Via the `mmproj` parameter (multimodal projector file).
\*\* Via the `send_pictures` extension.