triton
SillyTavern
triton | SillyTavern | |
---|---|---|
30 | 75 | |
11,054 | 677 | |
4.3% | - | |
9.9 | 10.0 | |
3 days ago | 11 months ago | |
C++ | JavaScript | |
MIT License | GNU Affero General Public License v3.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
triton
- OpenAI Triton: language and compiler for highly efficient Deep-Learning
-
Show HN: Ollama for Linux – Run LLMs on Linux with GPU Acceleration
There's a ton of cool opportunity in the runtime layer. I've been keeping my eye on the compiler-based approaches. From what I've gathered many of the larger "production" inference tools use compilers:
- https://github.com/openai/triton
- Core Functionality for AMD #1983
- Project name easily confused with Nvidia triton
-
Nvidia's CUDA Monopoly
Does anyone have more inside knowledge from OpenAI or AMD on AMDGPU support for Triton?
I see this:
https://github.com/openai/triton/issues/1073
But it's not clear to me if we will see AMD GPUs as first class citizens for pytorch in the future?
- @soumithchintala (Cofounded and lead @PyTorch at Meta) on Twitter: I'm fairly puzzled by $NVDA skyrocketing... (cont.)
-
The tiny corp raised $5.1M
I thought this was a good overview of the idea Triton can circumvent the CUDA moat: https://www.semianalysis.com/p/nvidiaopenaitritonpytorch
It also looks like they added MLIR backend to Triton though I wonder if Mojo has advantages since it was built on MLIR? https://github.com/openai/triton/pull/1004
-
Anyone hosting a local LLM server
I'm pretty happy with the setup, because it allows me to keep all the AI stuff and its dozens of conda envs and repos etc. seperate from my normal setup and "portable". It may have some performance impact (although I don't personally notice any significant difference to running it "natively" on windows), and it may enable some extra functionality, such as access to OpenAi's Triton etc., but that's currently neither here nor there.
- Triton: Runtime for highly efficient custom Deep-Learning primitives
-
Mojo – a new programming language for all AI developers
Very cool development. There is too much busy work going from development to test to production. This will help to unify everything. OpenAI Triton https://github.com/openai/triton/ is going for a similar goal. But this is a more fundamental approach.
SillyTavern
-
Help😢
Go to Termix and click Exit. Then go to Termux and code 1. Apk update 2. Apk upgrade 3. git clone https://github.com/Cohee1207/SillyTavern 4. cd SillyTavern 5. Install nodejs 6. Npm install 7. Node server
-
Oogabooga and llama.cpp in longer conversations answers take forever.....
If you want the best roleplaying experience, I can only recommend SillyTavern with SillyTavern/SillyTavern-extras. The extras include summarization and ChromaDB, both helping to get longer and more coherent chats.
-
koboldcpp-1.33 Ultimate Edition released!
Really? Then we definitely have different experiences (or different ways to interact) with Guanaco. It's been the most unrestricted model I've tried, and I tried them all, but I'm using SillyTavern and the simple-proxy-for-tavern which combined with a little prompting liberates basically any model.
-
The best 13B model for rolepay?
Why reinvent the wheel? Just use SillyTavern, ideally with the simple-proxy-for-tavern. That does it all, and more.
-
airoboros gpt4 v1.2
I tested this today in an hours-long direct roleplay comparison between q3_K_M quants of TheBloke/airoboros-65B-gpt4-1.2-GGML and TheBloke/guanaco-65B-GGML, using koboldcpp as backend together with simple-proxy-for-tavern and SillyTavern as frontend.
-
What are you using for RP?
I'm using SillyTavern frontend and simple-proxy-for-tavern with koboldcpp backend.
-
KoboldCPP Updated to Support K-Quants, new bonus CUDA build.
I'm using SillyTavern frontend and simple-proxy-for-tavern with koboldcpp. Not sure which of these has solved the prompt-reprocessing problem, but I no longer have these slowdowns.
-
What are your favorite LLMs?
WizardLM 30B V1.0 is not only smarter and follows instructions better than the others, it's even uncensored when used with an uncensoring character card (I use SillyTavern as my GUI/frontend) - more so than any other model I tested. Probably because it follows instructions so well, thus roleplaying an uncensored character properly (and not breaking character or going "as an AI" even once during my tests).
-
Potato's brain guide to installing and reopening SillyTavern for Mac
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.3/install.sh | bash export NVM_DIR="$([ -z "${XDG_CONFIG_HOME-}" ] && printf %s "${HOME}/.nvm" || printf %s "${XDG_CONFIG_HOME}/nvm")" [ -s "$NVM_DIR/nvm.sh" ] && \. "$NVM_DIR/nvm.sh" nvm install node git clone -b dev https://github.com/Cohee1207/SillyTavern && cd SillyTavern npm i && node server.js
-
I've found a solution to Poe API error
For Android (Termux users): 1. apt update 2. apt upgrade 3. Type "y" to everything and hit enter 4. pkg install git 5. git clone -b dev https://github.com/Cohee1207/SillyTavern 6. cd SillyTavern 7. pkg install nodejs 8. npm install 9. bash start.sh
What are some alternatives?
cuda-python - CUDA Python Low-level Bindings
koboldcpp - A simple one-file way to run various GGML and GGUF models with KoboldAI's UI
Halide - a language for fast, portable data-parallel computation
TavernAI - TavernAI for nerds [Moved to: https://github.com/Cohee1207/SillyTavern]
GPU-Puzzles - Solve puzzles. Learn CUDA.
langflow - ⛓️ Langflow is a dynamic graph where each node is an executable unit. Its modular and interactive design fosters rapid experimentation and prototyping, pushing hard on the limits of creativity.
dfdx - Deep learning in Rust, with shape checked tensors and neural networks
character-editor - Create, edit and convert AI character files for CharacterAI, Pygmalion, Text Generation, KoboldAI and TavernAI
web-llm - Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.
simple-proxy-for-tavern
cutlass - CUDA Templates for Linear Algebra Subroutines
ChatRWKV - ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.