OlivierDehaene 12590fdcce feat: paged attention v2 (#1183)		2023-10-23 12:29:25 +02:00
..
awq/quantize	feat: format code (#1070)	2023-09-27 12:22:09 +02:00
gptq	feat: format code (#1070)	2023-09-27 12:22:09 +02:00
__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	Fix window_size_left for flash attention v1 (#1089)	2023-10-02 20:53:14 +02:00
hub.py	feat(server): Adding new ignore_rule for conversion. (#485)	2023-06-23 12:41:13 +02:00
layers.py	fix: EETQLinear with bias in layers.py (#1176)	2023-10-19 12:15:05 +02:00
logits_process.py	fix(server): avoid errors for very small top_p values (#544)	2023-07-04 20:11:33 +02:00
paged_attention.py	feat: paged attention v2 (#1183)	2023-10-23 12:29:25 +02:00
peft.py	feat: format code (#1070)	2023-09-27 12:22:09 +02:00
tokens.py	fix: type hint typo in tokens.py (#1102)	2023-10-05 09:33:04 +02:00
watermark.py	Fixing watermark. (#851)	2023-08-16 07:17:26 +02:00
weights.py	Fixing GPTQ exllama kernel usage. (#1101)	2023-10-05 10:11:27 +02:00