oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-04 22:27:29 +00:00
Code Issues Projects Releases Packages Wiki Activity

Add cache_4bit option for ExLlamaV2 (#5645)

Browse source
This commit is contained in:
oobabooga 2024-03-06 23:02:25 -03:00 • committed by GitHub
parent fa0e68cefd
commit 2ec1d96c91
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 28 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -139,6 +139,7 @@ group.add_argument('--max_seq_len', type=int, default=2048, help='Maximum sequen
group.add_argument('--cfg-cache', action='store_true', help='ExLlamav2_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader.')
group.add_argument('--no_flash_attn', action='store_true', help='Force flash-attention to not be used.')
group.add_argument('--cache_8bit', action='store_true', help='Use 8-bit cache to save VRAM.')
group.add_argument('--cache_4bit', action='store_true', help='Use 4-bit cache to save VRAM.')
group.add_argument('--num_experts_per_token', type=int, default=2, help='Number of experts to use for generation. Applies to MoE models like Mixtral.')
# AutoGPTQ