ollama-ui
lmdeploy
ollama-ui | lmdeploy | |
---|---|---|
2 | 4 | |
554 | 2,482 | |
- | 15.8% | |
7.2 | 9.8 | |
18 days ago | 6 days ago | |
JavaScript | Python | |
MIT License | 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.
ollama-ui
-
Dumbar, a Not So Smart Menubar App
This is great. I was thinking about putting something like this together for personal use, so - thanks for saving us the trouble!
Ollama support would be amazing, especially with the recent integration of codellama and phind-codellama. I’m sure you’re aware, but for the benefit of anyone else: there is a third party Ollama web ui[1] linked to from the ollama project homepage. It’s barebones, but does the trick.
[1]: https://github.com/ollama-ui/ollama-ui
- 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?
aider - aider is AI pair programming in your terminal
vllm - A high-throughput and memory-efficient inference and serving engine for LLMs
llama.cpp - LLM inference in C/C++
Dumbar - A smrt, no, smart, ok, no dumb smartbar for Ollama
llama-cpp-python - Python bindings for llama.cpp
tabby - Self-hosted AI coding assistant
CTranslate2 - Fast inference engine for Transformer models
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
smartcat
seamless_communication - Foundational Models for State-of-the-Art Speech and Text Translation