pytorch / torchchatLinks
Run PyTorch LLMs locally on servers, desktop and mobile
☆3,615Updated last month
Alternatives and similar repositories for torchchat
Users that are interested in torchchat are comparing it to the libraries listed below
Sorting:
- PyTorch native post-training library☆5,535Updated last week
- A PyTorch native platform for training generative AI models☆4,561Updated this week
- ☆3,031Updated last year
- On-device AI across mobile, embedded and edge for PyTorch☆3,310Updated this week
- nanoGPT style version of Llama 3.1☆1,432Updated last year
- MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.☆1,379Updated 6 months ago
- PyTorch native quantization and sparsity for training and inference☆2,438Updated this week
- Build your own inference engine with expert control. Deploy agents, MCP servers, models, RAG, pipelines and more. No MLOps. No YAML.☆3,591Updated this week
- PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily wri…☆1,414Updated last week
- An Extensible Deep Learning Library☆2,271Updated this week
- NanoGPT (124M) in 3 minutes☆3,565Updated this week
- Agentic components of the Llama Stack APIs☆4,274Updated 2 months ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,128Updated last month
- Minimalistic large language model 3D-parallelism training☆2,267Updated last month
- The n-gram Language Model☆1,454Updated last year
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,729Updated 3 months ago
- ☆4,100Updated last year
- DataComp for Language Models☆1,375Updated last month
- Everything about the SmolLM and SmolVLM family of models☆3,314Updated last month
- Tools for merging pretrained large language models.☆6,378Updated last month
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,021Updated last year
- Training LLMs with QLoRA + FSDP☆1,527Updated 11 months ago
- Efficient Triton Kernels for LLM Training☆5,752Updated this week
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,673Updated last week
- Implementation for MatMul-free LM.☆3,034Updated 3 months ago
- llama3.np is a pure NumPy implementation for Llama 3 model.☆989Updated 5 months ago
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆3,484Updated 5 months ago
- Video+code lecture on building nanoGPT from scratch☆4,443Updated last year
- lightweight, standalone C++ inference engine for Google's Gemma models.☆6,591Updated this week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆1,856Updated last month