serving
llama.cpp
Our great sponsors
serving | llama.cpp | |
---|---|---|
12 | 769 | |
6,071 | 56,891 | |
0.2% | - | |
9.8 | 10.0 | |
3 days ago | about 15 hours ago | |
C++ | C++ | |
Apache License 2.0 | MIT License |
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.
serving
-
Llama.cpp: Full CUDA GPU Acceleration
Yet another TEDIOUS BATTLE: Python vs. C++/C stack.
This project gained popularity due to the HIGH DEMAND for running large models with 1B+ parameters, like `llama`. Python dominates the interface and training ecosystem, but prior to llama.cpp, non-ML professionals showed little interest in a fast C++ interface library. While existing solutions like tensorflow-serving [1] in C++ were sufficiently fast with GPU support, llama.cpp took the initiative to optimize for CPU and trim unnecessary code, essentially code-golfing and sacrificing some algorithm correctness for improved performance, which isn't favored by "ML research".
NOTE: In my opinion, a true pioneer was DarkNet, which implemented the YOLO model series and significantly outperformed others [2]. Same trick basically like llama.cpp
[1] https://github.com/tensorflow/serving
-
[D] How do OpenAI and other companies manage to have real-time inference on model with billions of parameters over an API?
I mean, probably - it's written in C++ https://github.com/tensorflow/serving
-
Should I wait for the M2 Macbook Pro?
We’re looking into that solution at the moment, the issue I’m referring to is related to this https://github.com/tensorflow/serving/issues/1948 we’ll know if the plug-in approach works for our uses soon but haven’t started looking into implementing it yet
- TF Serving has been unavailable for 9 days so far due to outdated GPG key
- TF Serving has been unavailable for 8 days
-
Would you use maturin for ML model serving?
Which ML framework do you use? Tensorflow has https://github.com/tensorflow/serving. You could also use the Rust bindings to load a saved model and expose it using one of the Rust HTTP servers. It doesn't matter whether you trained your model in Python as long as you export its saved model.
-
Is LaMDA Sentient? – An Interview [pdf]
Most likely it's a model server running something like https://github.com/tensorflow/serving and if there isn't a lot of load, the resource could kill some of its tasks. I wouldn't imagine it's sitting around pondering deep thoughts.
-
Ask HN: How to deploy a TensorFlow model for access through an HTTP endpoint?
https://github.com/tensorflow/serving
https://thenewstack.io/tutorial-deploying-tensorflow-models-...
-
Popular Machine Learning Deployment Tools
GitHub
-
If data science uses a lot of computational power, then why is python the most used programming language?
You serve models via https://www.tensorflow.org/tfx/guide/serving which is written entirely in C++ (https://github.com/tensorflow/serving/tree/master/tensorflow_serving/model_servers), no Python on the serving path or in the shipped product.
llama.cpp
-
Phi-3 Weights Released
well https://github.com/ggerganov/llama.cpp/issues/6849
- Lossless Acceleration of LLM via Adaptive N-Gram Parallel Decoding
- Llama.cpp Working on Support for Llama3
-
Embeddings are a good starting point for the AI curious app developer
Have just done this recently for local chat with pdf feature in https://recurse.chat. (It's a macOS app that has built-in llama.cpp server and local vector database)
Running an embedding server locally is pretty straightforward:
- Get llama.cpp release binary: https://github.com/ggerganov/llama.cpp/releases
- Mixtral 8x22B
- Llama.cpp: Improve CPU prompt eval speed
-
Ollama 0.1.32: WizardLM 2, Mixtral 8x22B, macOS CPU/GPU model split
Ah, thanks for this! I can't edit my parent comment that you replied to any longer unfortunately.
As I said, I only compared the contributors graphs [0] and checked for overlaps. But those apparently only go back about year and only list at most 100 contributors ranked by number of commits.
[0]: https://github.com/ollama/ollama/graphs/contributors and https://github.com/ggerganov/llama.cpp/graphs/contributors
-
KodiBot - Local Chatbot App for Desktop
KodiBot is a desktop app that enables users to run their own AI chat assistants locally and offline on Windows, Mac, and Linux operating systems. KodiBot is a standalone app and does not require an internet connection or additional dependencies to run local chat assistants. It supports both Llama.cpp compatible models and OpenAI API.
-
Mixture-of-Depths: Dynamically allocating compute in transformers
There are already some implementations out there which attempt to accomplish this!
Here's an example: https://github.com/silphendio/sliced_llama
A gist pertaining to said example: https://gist.github.com/silphendio/535cd9c1821aa1290aa10d587...
Here's a discussion about integrating this capability with ExLlama: https://github.com/turboderp/exllamav2/pull/275
And same as above but for llama.cpp: https://github.com/ggerganov/llama.cpp/issues/4718#issuecomm...
-
The lifecycle of a code AI completion
For those who might not be aware of this, there is also an open source project on GitHub called "Twinny" which is an offline Visual Studio Code plugin equivalent to Copilot: https://github.com/rjmacarthy/twinny
It can be used with a number of local model services. Currently for my setup on a NVIDIA 4090, I'm running both the base and instruct model for deepseek-coder 6.7b using 5_K_M Quantization GGUF files (for performance) through llama.cpp "server" where the base model is for completions and the instruct model for chat interactions.
llama.cpp: https://github.com/ggerganov/llama.cpp/
deepseek-coder 6.7b base GGUF files: https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-GGU...
deepseek-coder 6.7b instruct GGUF files: https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct...
What are some alternatives?
server - The Triton Inference Server provides an optimized cloud and edge inferencing solution.
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
MNN - MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba
gpt4all - gpt4all: run open-source LLMs anywhere
flashlight - A C++ standalone library for machine learning
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
XLA.jl - Julia on TPUs
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
oneflow - OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
ggml - Tensor library for machine learning
glow - Compiler for Neural Network hardware accelerators
alpaca.cpp - Locally run an Instruction-Tuned Chat-Style LLM