mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2026-04-09 00:23:38 +00:00
API: Add parallel request support for llama.cpp and ExLlamaV3
This commit is contained in:
parent
2f08dce7b0
commit
9824c82cb6
10 changed files with 198 additions and 63 deletions
|
|
@ -151,6 +151,7 @@ def list_model_elements():
|
|||
'no_mmap',
|
||||
'mlock',
|
||||
'numa',
|
||||
'parallel',
|
||||
'use_double_quant',
|
||||
'bf16',
|
||||
'enable_tp',
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue