zengxiao-he/tessera
From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracl
- Stars
- 558
- Forks
- 8
- Open issues
- 2
- Last push
- 12d ago
About tessera
tessera is a free, open-source machine learning tool by zengxiao-he, written mainly in Python. From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracl. It has 558 GitHub stars and 8 forks, and was last updated 12d ago. GitHub doesn't detect a standard license, so check the repository before using it commercially. According to the project, it runs on a regular CPU without a GPU and works on macOS.
- License
- Not detected
- Language
- Python
- Stars
- 558
- Last update
- 12d ago
- Runs on Mac
- Yes (as stated by the project)
- GPU
- Not needed (runs on CPU)
- Paid API key
- Not stated
- Self-hostable
- Yes
Similar free tools
pytorch-image-models37k stars · The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT)
neural-compressor2.7k stars · SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
bitsandbytes8.5k stars · Accessible large language models via k-bit quantization for PyTorch.
AngelSlim1.8k stars · Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
Jackrong-llm-finetuning-guide1.7k stars · An educational, end-to-end open-source knowledge base for LLM fine-tuning, dataset distillation, reinforcement learning, and local deployment.
pmetal330 stars · PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.
tessera FAQ
Is tessera free?
Yes. tessera is open source and free to use. GitHub doesn't detect a standard license, so check the repository before using it commercially.
Does tessera run on a Mac?
Yes. According to the project, tessera works on macOS.
Does tessera need a GPU?
No. According to the project, tessera runs on a regular CPU.
Is tessera still maintained?
Yes. It was last updated 12d ago and has 2 open issues on GitHub.
What are alternatives to tessera?
Similar free, open-source tools include pytorch-image-models, neural-compressor, bitsandbytes, AngelSlim.