BigDL
llamafile
| BigDL | llamafile | |
|---|---|---|
| 5 | 39 | |
| 6,138 | 16,345 | |
| 2.9% | 15.2% | |
| 9.9 | 9.7 | |
| 6 days ago | 5 days ago | |
| Python | C++ | |
| Apache License 2.0 | GNU General Public License v3.0 or later |
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.
BigDL
- PyTorch Library for Running LLM on Intel CPU and GPU
-
LLaMA Now Goes Faster on CPUs
Any performance benchmark against intel's 'IPEX-LLM'[0] or others?
[0] - https://github.com/intel-analytics/ipex-llm
- BigDL-LLM: running LLM on your laptop using INT4
- Fast, distributed, secure AI for Big Data
-
Machine learning on JVM
Intel BigDL for Spark which again is for Spark.
llamafile
-
Firefox 127
Do you want that integrated in the browser? Because Mozilla already distributes offline LLMs: https://github.com/Mozilla-Ocho/llamafile
- Llamafile 0.8.6 CPU Benchmark
-
Ask HN: Which LLMs can run locally on most consumer computers
See https://github.com/Mozilla-Ocho/llamafile, a standalone packaging of llama.cpp that runs an LLM locally. It will use the GPU, but it also falls back on the CPU. CPU performance of small, quantized models is still pretty decent, and the page has estimated memory requirements for different models.
- Llamafile 0.8.2 Release with Embedding Subcmd in CLI and Performance Boost
- FLaNK-AIM Weekly 06 May 2024
- llamafile v0.8
-
Mistral AI Launches New 8x22B Moe Model
I think the llamafile[0] system works the best. Binary works on the command line or launches a mini webserver. Llamafile offers builds of Mixtral-8x7B-Instruct, so presumably they may package this one up as well (potentially a quantized format).
You would have to confirm with someone deeper in the ecosystem, but I think you should be able to run this new model as is against a llamafile?
[0] https://github.com/Mozilla-Ocho/llamafile
-
Apple Explores Home Robotics as Potential 'Next Big Thing'
Thermostats: https://www.sinopetech.com/en/products/thermostat/
I haven't tried running a local text-to-speech engine backed by an LLM to control Home Assistant. Maybe someone is working on this already?
TTS: https://github.com/SYSTRAN/faster-whisper
LLM: https://github.com/Mozilla-Ocho/llamafile/releases
LLM: https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-D...
It would take some tweaking to get the voice commands working correctly.
-
LLaMA Now Goes Faster on CPUs
While I did not succeed in making the matmul code from https://github.com/Mozilla-Ocho/llamafile/blob/main/llamafil... work in isolation, I compared eigen, openblas, and mkl: https://gist.github.com/Dobiasd/e664c681c4a7933ef5d2df7caa87...
In this (very primitive!) benchmark, MKL was a bit better than eigen (~10%) on my machine (i5-6600).
Since the article https://justine.lol/matmul/ compared the new kernels with MLK, we can (by transitivity) compare the new kernels with Eigen this way, at least very roughly for this one use-case.
-
Llamafile 0.7 Brings AVX-512 Support: 10x Faster Prompt Eval Times for AMD Zen 4
Yes, they're just ZIP files that also happen to be actually portable executables.
https://github.com/Mozilla-Ocho/llamafile?tab=readme-ov-file...
What are some alternatives?
Apache Spark - Apache Spark - A unified analytics engine for large-scale data processing
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
Axle - Axle Domain Specific Language for Scientific Cloud Computing and Visualization
ollama-webui - ChatGPT-Style WebUI for LLMs (Formerly Ollama WebUI) [Moved to: https://github.com/open-webui/open-webui]
Zeppelin - Web-based notebook that enables data-driven, interactive data analytics and collaborative documents with SQL, Scala and more.
langchain - 🦜🔗 Build context-aware reasoning applications
Spire - Powerful new number types and numeric abstractions for Scala.
LLaVA - [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
deequ - Deequ is a library built on top of Apache Spark for defining "unit tests for data", which measure data quality in large datasets.
safetensors - Simple, safe way to store and distribute tensors
PredictionIO - PredictionIO, a machine learning server for developers and ML engineers.
llama.cpp - LLM inference in C/C++