Token compression for LLM prompts via a learned token selector.
☆15Mar 10, 2026Updated 4 months ago
Alternatives and similar repositories for untoken
Users that are interested in untoken are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆12Jun 2, 2023Updated 3 years ago
- Composition of Multimodal Language Models From Scratch☆15Aug 16, 2024Updated last year
- Tinker feedback tracker☆41Dec 11, 2025Updated 7 months ago
- ☆24Oct 3, 2025Updated 9 months ago
- ☆26Feb 13, 2026Updated 5 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆19Feb 11, 2026Updated 5 months ago
- ☆33Jul 9, 2026Updated last week
- Auto-tuning for vllm. Getting the best performance out of your LLM deployment (vllm+guidellm+optuna)☆64Jun 12, 2026Updated last month
- This is a demo program for using OpenCV3.0 with Swift and C++.☆13Dec 3, 2014Updated 11 years ago
- 📸 gotta find 'em all; spatial reasoning benchmark for LLMs☆166Feb 1, 2026Updated 5 months ago
- 100 days of LLM inference engineering — daily posts, experiments, and visualizations☆102Apr 30, 2026Updated 2 months ago
- Zoof is a high-efficiency Small Language Model (SLM) engineered from scratch. It demonstrates how modern architectural choices and high-q…☆47Jan 13, 2026Updated 6 months ago
- You can using Follow_Your_Emoji in ComfyUI☆17Apr 11, 2025Updated last year
- How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks, ICLR 2026☆72Mar 6, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Swift source code to demonstrate loading and texturing a .OBJ file using ModelIO☆27Nov 23, 2023Updated 2 years ago
- [ICCV2025] WikiAutoGen offical page☆25Feb 6, 2026Updated 5 months ago
- Implementation of SmoothCache, a project aimed at speeding-up Diffusion Transformer (DiT) based GenAI models with error-guided caching.☆48Jul 17, 2025Updated last year
- ☆38Feb 6, 2025Updated last year
- Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation (D-SDS) | NeurIPS 2023☆46Feb 18, 2024Updated 2 years ago
- Extension for Sequential Image Inpainting Available in ComfyUI☆48Jun 29, 2025Updated last year
- OpenAI's Realtime API minus the enterprise bloat☆50Nov 21, 2024Updated last year
- the BLAKE3 hash function implemented in 6502 assembly☆58Feb 12, 2022Updated 4 years ago
- mkinf SDK to interact with mkinf hub MCP servers☆134Mar 17, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- comfyui custom nodes to support the Arc2Face diffusion model☆53Sep 2, 2024Updated last year
- This is the project for DreamStone: TPAMI & ISS: ICLR 2023 spotlight☆45Sep 23, 2023Updated 2 years ago
- Landing repository for the paper "Predicting the Order of Upcoming Tokens Improves Language Modeling"☆48May 13, 2026Updated 2 months ago
- Pytorch implementation of SinMPI (SIGGRAPH Asia 2023)☆61Aug 23, 2024Updated last year
- Proof of concept: Exploiting temporal coherence in LLM inference-- delta encoding for KV cache compression and weight-skip prediction. …☆50Apr 10, 2026Updated 3 months ago
- ☆58Mar 26, 2025Updated last year
- Diffusers wrapper for FollowYourEmoji☆64Apr 18, 2025Updated last year
- LLM training on Apple's Neural Engine — native Obj-C, private APIs, zero GPU. Dynamic weight pipeline for training without kernel recompi…☆56Mar 17, 2026Updated 4 months ago
- A coding agent framework, that works on its own codebase.☆371Apr 23, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- converts url content into JSON with a simple prefix☆73May 8, 2024Updated 2 years ago
- A byte-level decoder architecture that matches the performance of tokenized Transformers.☆68Apr 24, 2024Updated 2 years ago
- E-ink IBM XT clone with solar power, ultra low power consumption, and ultra long battery life.☆704Jan 28, 2025Updated last year
- Official code release for the paper: Sketch-guided Text-based 3D Editing☆53Sep 24, 2023Updated 2 years ago
- Code repository for the paper "MrT5: Dynamic Token Merging for Efficient Byte-level Language Models."☆59Sep 25, 2025Updated 9 months ago
- A Deep Research agent from scratch☆221May 18, 2025Updated last year
- Trust your gut on git☆63Jul 30, 2025Updated 11 months ago