Skip to content
English

Switch theme

Discover▾

Not sure where to start? This week’s hottest software, models and stacks in three minutes.

AI Apps▾

AI software people use: from assistants like ChatGPT to tools for coding, video and workflows, picked by purpose.

For Agents▾

Software for AI: tools that let your agent (Claude Code, Codex, Cursor…) browse, read docs, run code and remember.

Models▾

Choose models, estimate cost, self-host: prices, rankings, benchmarks, free tiers and compute.

Solutions▾

A goal or an error message? Ready-made stacks, steps and fixes by scenario.

Learn▾

A systematic course from zero to the frontier, with an algorithm library, must-read papers and tutorials.

Frontier▾

Daily AI news, weekly highlights, the latest papers and how AI is changing every discipline.

// Inference & local runtime

meta-pytorch/gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Official · Meta PyTorchBSD-3-Clause

GitHub ↗

01Overview

meta-pytorch/gpt-fast is an official Meta PyTorch repository in our “Inference & local runtime” category, written mainly in Python and licensed under BSD-3-Clause. As of 2026-10-23 it has 6,259 stars and 582 forks, ranking #40 of 62 tracked Inference & local runtime repos and #732 of all 1046 repos we track. It was created on 2023-10-17 (about 3 years ago); the latest commit is from 2025-08-22, with no commits for 427 days. There are no GitHub releases; install from source as described in the README.

No releases in the last 30 days.

02More from Meta PyTorch

Vendor page →
  • torchtune ★ 5,819 · Training & fine-tuning
  • captum ★ 5,714 · Eval, observability & guardrails
  • botorch ★ 3,632 · Training & fine-tuning

03Same category

All repos →
ggml-org/llama.cpp LLM inference in C/C++ Inference & local runtime · official★ 132k vllm-project/vllm A high-throughput and memory-efficient inference and serving engine for LLMs Inference & local runtime · official★ 95.2k mudler/LocalAI LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. Inference & local runtime★ 49.9k exo-explore/exo Run frontier AI locally. Inference & local runtime★ 48.0k ray-project/ray Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads. Inference & local runtime★ 44.1k

FAQ

What licence does gpt-fast use?

BSD-3-Clause, as shown on GitHub. Check the LICENSE file in meta-pytorch/gpt-fast before commercial use.

Is gpt-fast still maintained?

The last commit was on 2025-08-22 (427 days before 2026-10-23).

How popular is gpt-fast among Inference & local runtime projects?

#40 of 62 by stars (6,259). The most-starred in this category is ggml-org/llama.cpp (132k).

Data updated: GitHub OSS radar(UTC+8)