Slow-Fast Inference: Training-free Inference Acceleration via Within-sentence Support Stability
☆19Sep 2, 2026Updated 2 months ago
Alternatives and similar repositories for SFI
Users that are interested in SFI are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- OpenCV Python wrapper example for CUDA function☆11Jan 5, 2022Updated 4 years ago
- ☆17Mar 17, 2023Updated 3 years ago
- HEtero-Assists Distillation for Heterogeneous Object Detectors☆10Jul 3, 2023Updated 3 years ago
- Extracting graph data from smart contract source code☆14Feb 28, 2023Updated 3 years ago
- Official code of GIND (Optimization-Induced Graph Implicit Nonlinear Diffusion)☆18Jun 29, 2022Updated 4 years 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.
- Codes for the paper "Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex"☆21Jul 25, 2020Updated 6 years ago
- An MCP server to read MCP logs to debug directly inside the client☆16May 3, 2025Updated last year
- 基于电商导购机器人,自然语言理解(NLU),文本纠错,歧义词消歧☆12May 5, 2020Updated 6 years ago
- The fastest off-the-shelf inference algorithm for LLMs (ICLR’25)☆14Mar 8, 2025Updated last year
- ☆11Jun 19, 2025Updated last year
- 实现简单的 Spring IoC 框架☆19Mar 6, 2019Updated 7 years ago
- A trust layer between AI agents and your codebase. 🚀 Enterprise AI Agent Ecosystem - 40 Claude Code subagents for strategic leadership, …☆17Aug 20, 2026Updated 2 months ago
- AgentX Harness - Realistic 1mil Long Context, Multi Turn Agentic Workload Trace Replayer, collected from over $3mil USD of Traces | Agent…☆49Updated this week
- Go implementation of Recursive Language Models (RLM) - inference-time scaling for arbitrarily long contexts☆21May 12, 2026Updated 6 months 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.
- Overflow Prevention Enhances Long-Context Recurrent LLMs (COLM 2025)☆19Jul 8, 2025Updated last year
- Tool for generating tagged sentences from JSGF grammars☆16Dec 14, 2018Updated 7 years ago
- 「城语」APP基于A级景区、历史古迹、文物保护单位等基础数据,利用先进的大模型能力实现智能化的Citywalk 路线规划,包括设计一条路线、生成路线攻略、生成景点的推荐理由等三大核心功能;利用大模型减少了人工编辑和推荐的工作量,并可以根据游客的需求进行个性化定制,提升了游客…☆20Feb 20, 2024Updated 2 years ago
- LLM Agents: Landing Page Generation for an E-commerce Platform Using CrewAI, Groq-LangChain and Qdrant☆15May 30, 2024Updated 2 years ago
- FastAPI to serve Qwen-ASR with streaming support. Tested. Benchmarked. Flash Attention 2. Fast & Stable.☆16Jun 24, 2026Updated 4 months ago
- A smart VS-Code extension☆16Dec 13, 2022Updated 3 years ago
- Tile primitives for speedy kernels☆21Sep 13, 2026Updated 2 months ago
- ☆18Dec 22, 2025Updated 10 months ago
- Official training code for MUG-V 10B video generation model. Built on Megatron-LM (v0.14.0) with production-ready distributed training fo…☆26Oct 20, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [ICLR 2023] Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions☆28Feb 11, 2025Updated last year
- The code for Differentiable Linearized ADMM (ICML 2019)☆36Oct 9, 2019Updated 7 years ago
- ☆17Jun 10, 2025Updated last year
- ☆12Nov 21, 2022Updated 3 years ago
- numerical optimizaiton methods with msnhnet☆13Jun 11, 2021Updated 5 years ago
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆19Jul 10, 2025Updated last year
- PegaFlow is a high-performance KV cache offloading solution for vLLM v1 on single-node multi-GPU setups.☆25Jan 7, 2026Updated 10 months ago
- GPU monitor for Linux terminal supporting single or multiple gpu's in realtime☆23Oct 20, 2026Updated 3 weeks ago
- Visualize the Expert Parallelism Load Balancer☆19Mar 15, 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.
- ☆16Nov 21, 2017Updated 8 years ago
- Saving the process to install OpenCV for Python 3 with CUDA bindings☆44Sep 27, 2024Updated 2 years ago
- Unofficial implementation of Token Recycling self-speculative decoding method.☆10Nov 22, 2024Updated last year
- ☆19Mar 11, 2025Updated last year
- Github老玩家自己搭的服务器,老飞飞原版,可联机-天马座☆10May 14, 2019Updated 7 years ago
- ☆22Sep 17, 2026Updated 2 months ago
- ☆138Updated this week
Are these results useful?