17 commits

Author	SHA1	Message	Date
Bartowski	104573f7d4	Update cache_4bit documentation (#5649) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2024-03-07 13:08:21 -03:00
oobabooga	2ec1d96c91	Add cache_4bit option for ExLlamaV2 (#5645)	2024-03-06 23:02:25 -03:00
oobabooga	d6bd71db7f	ExLlamaV2: fix loading when autosplit is not set	2024-02-17 12:54:37 -08:00
oobabooga	a6730f88f7	Add --autosplit flag for ExLlamaV2 (#5524)	2024-02-16 15:26:10 -03:00
oobabooga	f1f2c4c3f4	Add --num_experts_per_token parameter (ExLlamav2) (#4955)	2023-12-17 12:08:33 -03:00
oobabooga	c0655475ae	Add cache_8bit option	2023-11-02 11:23:04 -07:00
oobabooga	77abd9b69b	Add no_flash_attn option	2023-11-02 11:08:53 -07:00
oobabooga	fbac6d21ca	Add missing exception	2023-10-20 23:53:24 -07:00
turboderp	ae8cd449ae	ExLlamav2_HF: Convert logits to FP32 (#4310)	2023-10-18 23:16:05 -03:00
Forkoz	8cce1f1126	Exllamav2 lora support (#4229) ... --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2023-10-14 16:12:41 -03:00
tdrussell	cb26163a20	Fix off-by-one error in exllama_hf caching logic (#4145)	2023-10-05 12:20:56 -03:00
oobabooga	03dc69edc5	ExLlama_HF (v1 and v2) prefix matching	2023-09-19 13:12:19 -07:00
oobabooga	605ec3c9f2	Add a warning about ExLlamaV2 without flash-attn	2023-09-18 12:26:35 -07:00
Panchovix	34dc7306b8	Fix NTK (alpha) and RoPE scaling for exllamav2 and exllamav2_HF (#3897)	2023-09-13 02:35:09 -03:00
oobabooga	b7adf290fc	Fix ExLlama-v2 path issue	2023-09-12 17:42:22 -07:00
oobabooga	18e6b275f3	Add alpha_value/compress_pos_emb to ExLlama-v2	2023-09-12 15:02:47 -07:00
oobabooga	c2a309f56e	Add ExLlamaV2 and ExLlamav2_HF loaders (#3881)	2023-09-12 14:33:07 -03:00