codellama
lmdeploy
codellama | lmdeploy | |
---|---|---|
9 | 4 | |
15,154 | 2,482 | |
7.0% | 15.8% | |
5.5 | 9.8 | |
14 days ago | 1 day ago | |
Python | Python | |
GNU General Public License v3.0 or later | Apache License 2.0 |
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.
codellama
-
Meta AI releases Code Llama 70B
The github [0] hasn't been fully updated, but it links to a paper [1] that describes how the smaller code llama models were trained. It would be a good guess that this model is similar.
[0] https://github.com/facebookresearch/codellama
-
Open/Local LLM support for MineDojo/Voyager
This k8s application deploys an instance of Voyager along with a Fabric Minecraft server with required fabric mods. It assumes you have a local deployment of a Large Language Model (LLM) with 4K-8K token context length with a compatible OpenAI API, including embeddings support.
-
Code Llama Parameters
I have been playing with code Llama (the 7B python one). It does pretty well, but I don't understand what the parameters in the code mean and how I should modify them to work best on my hardware. I'm looking at the code in: https://github.com/facebookresearch/codellama/blob/main/llama/generation.py.
-
What frameworks or platforms to use for full fine tuning of Code Llama?
Should I use HuggingFace https://huggingface.co/codellama/CodeLlama-34b-hf or grab the model from Facebook https://github.com/facebookresearch/codellama?
- Code Llama Released
-
Meta just released its answer to GitHub Copilot, and it’s free
such rights.
https://github.com/facebookresearch/codellama/blob/main/LICE...
https://github.com/facebookresearch/llama/blob/main/LICENSE
-
Introducing Code Llama: A New Era of AI-Driven Coding
Bringing AI to the coding community: Code Llama is designed to support software engineers across sectors – including research, industry, and open-source projects. You can checkout the Github repo here.
-
Code Llama by MetaAI (released yesterday)
GIthub https://github.com/facebookresearch/codellama
- Meta: Code Llama, an AI Tool for Coding
lmdeploy
- FLaNK-AIM Weekly 06 May 2024
-
AMD May Get Across the CUDA Moat
I wouldn’t say ROCm code is “slower”, per se, but in practice that’s how it presents. References:
https://github.com/InternLM/lmdeploy
https://github.com/vllm-project/vllm
https://github.com/OpenNMT/CTranslate2
You know what’s missing from all of these and many more like them? Support for ROCm. This is all before you get to the really wildly performant stuff like Triton Inference Server, FasterTransformer, TensorRT-LLM, etc.
ROCm is at the “get it to work stage” (see top comment, blog posts everywhere celebrating minor successes, etc). CUDA is at the “wring every last penny of performance out of this thing” stage.
In terms of hardware support, I think that one is obvious. The U in CUDA originally stood for unified. Look at the list of chips supported by Nvidia drivers and CUDA releases. Literally anything from at least the past 10 years that has Nvidia printed on the box will just run CUDA code.
One of my projects specifically targets Pascal up - when I thought even Pascal was a stretch. Cue my surprise when I got a report of someone casually firing it up on Maxwell when I was pretty certain there was no way it could work.
A Maxwell laptop chip. It also runs just as well on an H100.
THAT is hardware support.
-
Nvidia Introduces TensorRT-LLM for Accelerating LLM Inference on H100/A100 GPUs
vLLM has healthy competition. Not affiliated but try lmdeploy:
https://github.com/InternLM/lmdeploy
In my testing it’s significantly faster and more memory efficient than vLLM when configured with AWQ int4 and int8 KV cache.
If you look at the PRs, issues, etc you’ll see there are many more optimizations in the works. That said there are also PRs and issues for some of the lmdeploy tricks in vllm as well (AWQ, Triton Inference Server, etc).
I’m really excited to see where these projects go!
- Meta: Code Llama, an AI Tool for Coding
What are some alternatives?
tabby - Self-hosted AI coding assistant
vllm - A high-throughput and memory-efficient inference and serving engine for LLMs
refact - WebUI for Fine-Tuning and Self-hosting of Open-Source Large Language Models for Coding
llama.cpp - LLM inference in C/C++
llama-cpp-python - Python bindings for llama.cpp
smartcat
CTranslate2 - Fast inference engine for Transformer models
Voyager - An Open-Ended Embodied Agent with Large Language Models
app-voyager - Kubernetes deployment for Voyager and Fabric Minecraft
seamless_communication - Foundational Models for State-of-the-Art Speech and Text Translation