From 2694ef45a36b98efa1cb81ff2989c4eaf5d27c00 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Mon, 4 Dec 2023 20:45:06 -0800 Subject: [PATCH 1/2] Do not limit API updates/second --- modules/text_generation.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/modules/text_generation.py b/modules/text_generation.py index c5bfceb78e..ca379fd730 100644 --- a/modules/text_generation.py +++ b/modules/text_generation.py @@ -93,9 +93,10 @@ def _generate_reply(question, state, stopping_strings=None, is_chat=False, escap last_update = time.time() yield reply - # Limit updates to 24 or 5 per second to avoid lag + # Limit updates to 24 or 5 per second to avoid lag in the Gradio UI + # API updates are not limited else: - min_update_interval = 0.2 if (shared.args.listen or shared.args.share) else 0.0417 + min_update_interval = 0 if not escape_html else 0.2 if (shared.args.listen or shared.args.share) else 0.0417 if cur_time - last_update > min_update_interval: last_update = cur_time yield reply From c03ae1a89b245ff33d486019518bb742605aeebd Mon Sep 17 00:00:00 2001 From: Penagwin <1349689+Penagwin@users.noreply.github.com> Date: Tue, 12 Dec 2023 15:18:20 -0500 Subject: [PATCH 2/2] Fixed the docker docs quick start to copy the nvidia dockerfile --- docs/09 - Docker.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/09 - Docker.md b/docs/09 - Docker.md index bddc527289..406abcbfcf 100644 --- a/docs/09 - Docker.md +++ b/docs/09 - Docker.md @@ -19,7 +19,7 @@ Use these commands to launch the image: ``` cd text-generation-webui -ln -s docker/{Dockerfile,docker-compose.yml,.dockerignore} . +ln -s docker/{nvidia/Dockerfile,docker-compose.yml,.dockerignore} . cp docker/.env.example .env # Edit .env and set TORCH_CUDA_ARCH_LIST based on your GPU model docker compose up --build