deepseek-ai/DeepSpec

Source
GitHub
First trending
Category
Model inference
GitHub stars
7,125
Main language
Python

This page introduces an external open-source repository. It is not an HDATF product.

deepseek-ai/DeepSpec

What it does

DeepSpec is a codebase for training and evaluating draft models for speculative decoding. It covers data preparation, draft model implementations, training against cached target model outputs and evaluation of acceptance on benchmark tasks.

How it helps ATF

Not related to our products. Listed because it appeared in the ranked lists.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

  • JustVugg/colibri
    An inference engine written in pure C with no engine dependencies that runs large mixture-of-experts models on consumer hardware. It treats VRAM, RAM and storage as one memory hierarchy and streams experts from disk.
  • diegosouzapw/OmniRoute
    OmniRoute is an MIT-licensed AI gateway that puts many model providers behind one endpoint for tools such as Claude Code, Codex, Cursor and Cline. It offers quota-aware fallback, token compression and a dashboard tracking provider free tiers.
  • router-for-me/CLIProxyAPI
    A Go proxy server that wraps CLI tools such as Codex, Claude Code, Antigravity and Grok Build behind OpenAI, Gemini and Claude compatible APIs. Compatible clients and SDKs can then reach those models, including through multiple CLI accounts.
  • google-research/timesfm
    TimesFM is a pretrained foundation model from Google Research for time-series forecasting. The latest version, 3.0, adds multivariate forecasting and support for past and future covariates.
  • Robbyant/lingbot-map
    A feed-forward model for streaming 3D reconstruction. Its Geometric Context Transformer uses anchor context, a pose reference window and trajectory memory to correct drift over long frame sequences.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.

View on GitHub (opens in a new tab)