pytorch / torchchatLinks
Run PyTorch LLMs locally on servers, desktop and mobile
☆3,599Updated 3 weeks ago
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☆5,366Updated this week
- ☆2,990Updated 10 months ago
- A PyTorch native platform for training generative AI models☆4,125Updated this week
- On-device AI across mobile, embedded and edge for PyTorch☆3,092Updated this week
- Everything about the SmolLM and SmolVLM family of models☆3,032Updated this week
- Agentic components of the Llama Stack APIs☆4,267Updated 3 months ago
- NanoGPT (124M) in 3 minutes☆2,892Updated 2 weeks ago
- Composable building blocks to build Llama Apps☆7,937Updated this week
- Training LLMs with QLoRA + FSDP☆1,524Updated 8 months ago
- Efficient Triton Kernels for LLM Training☆5,419Updated last week
- nanoGPT style version of Llama 3.1☆1,409Updated 11 months ago
- Modeling, training, eval, and inference code for OLMo☆5,822Updated last week
- The easiest way to deploy agents, MCP servers, models, RAG, pipelines and more. No MLOps. No YAML.☆3,427Updated this week
- MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.☆1,313Updated 3 months ago
- PyTorch native quantization and sparsity for training and inference☆2,219Updated this week
- Tools for merging pretrained large language models.☆6,122Updated this week
- The n-gram Language Model☆1,437Updated 11 months ago
- PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily wri…☆1,384Updated this week
- DataComp for Language Models☆1,342Updated 4 months ago
- Implementation for MatMul-free LM.☆3,018Updated last week
- Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.☆3,068Updated last week
- Blazingly fast LLM inference.☆5,923Updated this week
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,669Updated 2 weeks ago
- llama3.np is a pure NumPy implementation for Llama 3 model.☆987Updated 3 months ago
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,036Updated 3 months ago
- lightweight, standalone C++ inference engine for Google's Gemma models.☆6,514Updated this week
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆3,333Updated 2 months ago
- ☆3,886Updated 3 weeks ago
- A modern model graph visualizer and debugger☆1,288Updated last week
- Minimalistic large language model 3D-parallelism training☆2,068Updated 3 weeks ago