oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-06 15:13:38 +00:00
Code Issues Projects Releases Packages Wiki Activity

API: Add parallel request support for llama.cpp and ExLlamaV3

Browse source
This commit is contained in:
oobabooga 2026-03-05 16:49:58 -08:00
parent 2f08dce7b0
commit 9824c82cb6
10 changed files with 198 additions and 63 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/shared.py
View file

@ -102,6 +102,7 @@ group.add_argument('--ubatch-size', type=int, default=1024, help='Maximum number
group.add_argument('--threads', type=int, default=0, help='Number of threads to use.')
group.add_argument('--threads-batch', type=int, default=0, help='Number of threads to use for batches/prompt processing.')
group.add_argument('--numa', action='store_true', help='Activate NUMA task allocation for llama.cpp.')
group.add_argument('--parallel', type=int, default=1, help='Number of parallel request slots. The context size is divided equally among slots. For example, to have 4 slots with 8192 context each, set ctx_size to 32768.')
group.add_argument('--extra-flags', type=str, default=None, help='Extra flags to pass to llama-server. Format: "flag1=value1,flag2,flag3=value3". Example: "override-tensor=exps=CPU"')
# Transformers/Accelerate