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

@ -59,7 +59,7 @@ class Exllamav3Model:
logger.warning(f"max_num_tokens must be a multiple of 256. Adjusting from {max_tokens} to {adjusted_tokens}")
max_tokens = adjusted_tokens
# Parse cache type (ExLlamaV2 pattern)
# Parse cache type
cache_type = shared.args.cache_type.lower()
cache_kwargs = {}
if cache_type == 'fp16':