Speculative Decoding Implementations: MTP, EAGLE-3, Medusa-1, PARD, Draft Models, N-gram and Suffix Decoding from scratch
☆15May 2, 2026Updated 5 months ago
Alternatives and similar repositories for Speculative-Decoding
Users that are interested in Speculative-Decoding are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Multi-dataset evaluation of Anthropic's J-Space on Qwen3-4B. Demonstrates that internal 'workspace noise' can reliably route high-confide…☆13Jul 13, 2026Updated 3 months ago
- ☆14Apr 2, 2026Updated 6 months ago
- ☆16Feb 3, 2026Updated 8 months ago
- A simple, "Ollama-like" tool for managing and running GGUF language models from your terminal.☆25Jan 2, 2026Updated 9 months ago
- Harn is a programming language and runtime for building AI agents.☆27Oct 16, 2026Updated last week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- A web frontend for managing an EmpyrionServer (similar to the EAH), as a MOD so that it can also be used seemless in game hosting.☆24Aug 3, 2026Updated 2 months ago
- Tool schemas get re-prefilled on every LLM request. ContextCache compiles them into a KV cache once, stores it on disk and reuses it acro…☆22Sep 16, 2026Updated last month
- A bytebot variant that uses Holo 1.5 7b to control the desktop☆25Nov 4, 2025Updated 11 months ago
- ☆18Dec 1, 2025Updated 10 months ago
- LLM inference in C/C++☆34Aug 1, 2026Updated 2 months ago
- Chain two LLMs — local or cloud: a Prompter that refines your idea, and a Coder that writes the code.☆34Jul 18, 2026Updated 3 months ago
- Qwen3.8-Flash-Next 180B NVFP4 @ 231 tok/s on one RTX PRO 6000 Blackwell (sm120) - sglang patches, launchers, full optimization analysis☆30Aug 31, 2026Updated last month
- The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, …☆41Updated this week
- RL a search agent on SEC filings with Tinker (Dr. GRPO, gpt-oss-20b)☆24Sep 17, 2026Updated last month
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- A transparent (O)llama proxy with model deployment aware routing which auto-manages multiple (O)llama instances in a given network.☆20Apr 14, 2026Updated 6 months ago
- An educational Rust project for exporting and running inference on Qwen3 LLM family☆43Aug 3, 2025Updated last year
- Zero-instrumentation LLM API and MCP tracer for your agents powered by eBPF — latency, tokens, and tool use in realtime☆19Mar 16, 2026Updated 7 months ago
- Lightweight API Specification for Intelligent Systems☆17Sep 8, 2026Updated last month
- Mission control for your coding agents. See every session, know which one needs you, and jump straight to it. Your sessions stay in your …☆43Oct 15, 2026Updated last week
- Local LLM Search Index for RAG☆20May 5, 2026Updated 5 months ago
- An AI assistant for PCs powered by Meta's LLaMA3 using Hugging Face, runs on voice recognition, text-to-speech. Send messages, voice/vide…☆21Jun 6, 2024Updated 2 years ago
- Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines☆53Updated this week
- 3.34× faster inference on Apple Silicon: native MLX port of DFlash speculative decoding☆19Oct 7, 2026Updated 2 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Code for building self-expanding knowledge graphs with Outlines, vLLM, neo4j, and Modal.☆38May 14, 2025Updated last year
- ☆15Mar 18, 2026Updated 7 months ago
- A workbench for language model research☆98Aug 9, 2026Updated 2 months ago
- A node.js client for clojure NREPL servers☆11Aug 11, 2016Updated 10 years ago
- Dataset accompanying "PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Data" (pu…☆14Dec 4, 2024Updated last year
- Research code and scripts used in the Silburt et al. (2021) EMNLP 2021 paper 'FANATIC: FAst Noise-Aware TopIc Clustering'☆11Jul 6, 2023Updated 3 years ago
- A GUI to manage 2025 ROG Flow Z13 system settings via z13ctl's API.☆39Aug 14, 2026Updated 2 months ago
- Git-native shared memory for AI CLI agents☆38Jun 4, 2026Updated 4 months ago
- ☆20Jan 3, 2026Updated 9 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Use LLM as a logic gate/processor for local coding agent, context management customisation so the llm calls remains fast and small☆68Sep 3, 2026Updated last month
- A lightweight tool for running team retrospectives☆16Sep 1, 2026Updated last month
- makeyouravatar-zimage☆11Dec 10, 2025Updated 10 months ago
- ☆10May 9, 2019Updated 7 years ago
- ☆11Dec 20, 2025Updated 10 months ago
- ☆14Feb 22, 2024Updated 2 years ago
- Packaged externs for the Node.js standard library + utilities☆12Oct 24, 2017Updated 8 years ago