Remove ExLlamaV2 backend

- archived upstream: 7dc12af3a8
- replaced by ExLlamaV3, which has much better quantization accuracy
This commit is contained in:
oobabooga 2026-03-05 13:57:21 -08:00
parent 134ac8fc29
commit 2f08dce7b0
19 changed files with 22 additions and 713 deletions

View file

@ -6,8 +6,6 @@
| Transformers | ✅ | ✅ | ✅\*\* | ✅ |
| ExLlamav3_HF | ❌ | ❌ | ❌ | ✅ |
| ExLlamav3 | ❌ | ❌ | ✅ | ❌ |
| ExLlamav2_HF | ✅ | ❌ | ❌ | ✅ |
| ExLlamav2 | ✅ | ❌ | ❌ | ❌ |
| TensorRT-LLM | ❌ | ❌ | ❌ | ❌ |
❌ = not supported