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

ExLlamaV3: Enable the --enable-tp option, add a --tp-backend option

Browse source
This commit is contained in:
oobabooga 2025-08-17 13:19:11 -07:00
parent d771ca4a13
commit dbabe67e77
5 changed files with 16 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

5
modules/exllamav3.py
View file

@ -91,6 +91,11 @@ class Exllamav3Model:
split = [float(alloc) for alloc in shared.args.gpu_split.split(",")]
load_params['use_per_device'] = split
# Tensor-parallelism
if shared.args.enable_tp:
load_params['tensor_p'] = True
load_params['tp_backend'] = shared.args.tp_backend
model.load(**load_params)
tokenizer = Tokenizer.from_config(config)