OlivierDehaene 3a521c92b3 feat: mixtral (#1328)		2023-12-11 14:43:40 +01:00
..
awq/quantize	feat: format code (#1070)	2023-09-27 12:22:09 +02:00
gptq	Exllama v2 (#1211)	2023-11-25 22:38:38 +01:00
__init__.py	feat(server): Add native support for PEFT Lora models (#762)	2023-08-03 17:22:45 +02:00
convert.py	fit for baichuan models (#981)	2023-09-08 16:51:34 +02:00
dist.py	feat: add cuda memory fraction (#659)	2023-07-24 11:43:58 +02:00
flash_attn.py	Add RoCm support (#1243)	2023-11-27 14:08:12 +01:00
hub.py	feat(server): Adding new ignore_rule for conversion. (#485)	2023-06-23 12:41:13 +02:00
import_utils.py	Add RoCm support (#1243)	2023-11-27 14:08:12 +01:00
layers.py	feat: mixtral (#1328)	2023-12-11 14:43:40 +01:00
logits_process.py	fix(server): avoid errors for very small top_p values (#544)	2023-07-04 20:11:33 +02:00
medusa.py	Speculative (#1308)	2023-12-11 12:46:30 +01:00
paged_attention.py	feat: paged attention v2 (#1183)	2023-10-23 12:29:25 +02:00
peft.py	Fix missing trust_remote_code flag for AutoTokenizer in utils.peft (#1270)	2023-11-23 12:41:05 +01:00
speculate.py	Speculative (#1308)	2023-12-11 12:46:30 +01:00
tokens.py	Speculative (#1308)	2023-12-11 12:46:30 +01:00
watermark.py	Fixing watermark. (#851)	2023-08-16 07:17:26 +02:00
weights.py	Exllama v2 (#1211)	2023-11-25 22:38:38 +01:00