Lossless speculative decoding for HuggingFace causal language models, with a static-cache CUDA-graph fast path.
☆17Oct 29, 2026Updated this week
Alternatives and similar repositories for FlashSpec
Users that are interested in FlashSpec are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- my profile readme☆21Updated this week
- Intelligent Scientific Literature Explorer | Discover, compare, and organize research across arXiv, Semantic Scholar & OpenAlex — powered…☆21Jul 10, 2026Updated 3 months ago
- A modular, production-grade framework for Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimization (PPO) and D…☆28Jun 6, 2026Updated 4 months ago
- One library, four surfaces. Production-grade Kolmogorov-Arnold Networks || TensorFlow + PyTorch + ONNX. || A small KAN beats a 10× larger…☆38Updated this week
- Reproducible, production-grade pipelines for modern multimodal vision systems. Efficient VLM adaptation · Embedding-space drift detecti…☆59Aug 18, 2026Updated 2 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Production-grade multimodal RAG for financial document intelligence. Chart understanding · hybrid retrieval · numeric guardrails · multi-…☆92Oct 14, 2026Updated 2 weeks ago
- 60+ ML/AI/DL/RL/Bayesian algorithms implemented from scratch in NumPy -- plus mlscratch, a pip-installable package (pip install scratchki…☆40Oct 22, 2026Updated last week
- Chat App using React.js, Tailwind and for database and deployment using Firebase☆10Jul 17, 2024Updated 2 years ago
- A Chat App Created Using NextJS And Firebase☆11Jul 9, 2022Updated 4 years ago
- Simple, fast and user-friendly chat-app using ReactJS and Firebase.☆12Feb 4, 2022Updated 4 years ago
- ☆33Feb 26, 2013Updated 13 years ago
- The Python programming language☆107Dec 19, 2025Updated 10 months ago
- Integrate your CodersRank profile summary to your personal website☆23Nov 22, 2024Updated last year
- ☆14Feb 12, 2025Updated last year
- 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.
- This project is a semi-supervised approach to detect emotions on faces in-the-wild using GAN☆24Dec 8, 2022Updated 3 years ago
- ☆17Oct 9, 2026Updated 2 weeks ago
- ☆13Aug 29, 2026Updated 2 months ago
- ☆11Sep 26, 2024Updated 2 years ago
- API Hook Test for Taskmgr.exe☆11Jun 6, 2019Updated 7 years ago
- RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink☆18Oct 22, 2026Updated last week
- ☆10Aug 8, 2023Updated 3 years ago
- ☆12Sep 26, 2024Updated 2 years ago
- Agent skill to use Context Hub (chub)☆45Apr 23, 2026Updated 6 months ago
- 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.
- ☆21Oct 31, 2019Updated 6 years ago
- Personal collection of Agent Skills for AI coding agents (Claude Code, Gemini CLI, Cursor, Codex, etc.)☆19Jul 8, 2026Updated 3 months ago
- Telegram 频道查重 Bot☆22Jan 13, 2024Updated 2 years ago
- This is a realtime chat application built with Next.JS and Pusher☆36Mar 12, 2021Updated 5 years ago
- Game making library for using Canvas element☆116Oct 17, 2023Updated 3 years ago
- ☆15Oct 2, 2024Updated 2 years ago
- ☆19Oct 2, 2024Updated 2 years ago
- This is the latest KLCiS Voucher System embedded portal for Omada cloud/hardware controller. With this, the client can now check their pu…☆17Mar 6, 2025Updated last year
- Arche is a Greek word with primary senses "beginning". The repository defines a framework for technology mapping of emerging technologies…☆11May 15, 2020Updated 6 years 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.
- ☆12Jun 8, 2023Updated 3 years ago
- npu☆13Sep 5, 2018Updated 8 years ago
- A Walsh Hadamard Derived Linear Vector Symbolic Architecture☆13Jan 30, 2026Updated 9 months ago
- ☆13Oct 11, 2024Updated 2 years ago
- Hyperdimensional computing in memory. Artifact from 'A Case Study of Processing-in-Memory in off-the-Shelf Systems' (USENIX ATC '21)☆10Dec 2, 2023Updated 2 years ago
- ☆23Sep 7, 2025Updated last year
- Turn Claude Code into a full game dev studio — 48 AI agents, 36 workflow skills, and a complete coordination system mirroring real studio…☆19Mar 22, 2026Updated 7 months ago