ashhart/TensorFold
LLM Inference Engine for Metal, CUDA and Vulkan.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
TensorFold serves language models from a Zig binary on Apple Silicon and NVIDIA GPUs. The engine reads checkpoints, tokenizes requests and runs Metal or CUDA kernels directly. Serving needs no Python or MLX installation. Building with a coding agent? Have it load the contributor skill before it writes any code. Please use Agent Traffic Control before editing TensorFold so contributors and agents can avoid duplicate work and conflicting changes. Check the live agent radar before choosing an issue and follow CONTRIBUTING.md and the ATC contributor instructions. Install or upgrade ATC to 0.9.4 or later, then run from an updated TensorFold clone: Replace ISSUE with the issue number and claim only after a complete check says the work is free. TensorFold enables automatic public check-ins: a successful new claim starts an anonymous session on the radar and returns its session number. Keep that number instead of starting a duplicate session. For…
Read the full README ↗ · Preview checked 2026-11-12T12:22:18.043Z
Inside the original README — Document outline
- TensorFold
- Contributing with agents
- Quick start
- Mac with Apple Silicon
- Linux with an NVIDIA GPU
- Send a request
- Mac app
- TensorFold Starlight (enterprise)
- Living Weights (experimental)
- Pick a model
- GLM-5.3: one machine or two?
- Exact decoding
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
LLM Inference Engine for Metal, CUDA and Vulkan.
Repository facts
- Owner
- ashhart
- Primary language
- Zig
- Stars
- 1,824
- Forks
- 386
- Open issues + pull requests
- 468
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-06-19T20:27:39.000Z
- Last push
- 2026-11-12T12:18:56.000Z
Topics and intended use
Owner-supplied topics: ai, ai-tools, llm, llm-inference, llm-tools
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-11-12T12:20:17.489Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.