Artifact for "Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs" [arXiv '25]
☆21Jul 26, 2026Updated 3 months ago
Alternatives and similar repositories for failfast
Users that are interested in failfast are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆76Oct 2, 2025Updated last year
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆73Mar 5, 2025Updated last year
- ☆17May 10, 2024Updated 2 years ago
- Personal blog + reading notes on system-ish papers☆17Oct 29, 2023Updated 3 years ago
- 2023/12/22 电三 420 每周会议技术分享：「容器」的 slides 和附件☆10Dec 22, 2023Updated 2 years 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.
- ☆21Sep 6, 2026Updated last month
- Scalable Edge-Assisted Serving Framework for Interactive LLMs [NeurIPS 2025 Spotlight]☆38Nov 14, 2025Updated 11 months ago
- ☆18May 16, 2026Updated 5 months ago
- The official repo for the paper "Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching"☆17Mar 17, 2025Updated last year
- ☆13Feb 22, 2023Updated 3 years ago
- ☆25Nov 27, 2025Updated 11 months ago
- Tiny-Megatron, a minimalistic re-implementation of the Megatron library☆31Sep 1, 2025Updated last year
- UI-CTX: demystifying Android UI behaviors with a concise and effective representation, in NDSS '25☆14Jan 17, 2025Updated last year
- A git repository with hands-on material for Data Science on KSL plattaforms☆14Oct 27, 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.
- ☆12May 18, 2020Updated 6 years ago
- ☆44Jun 23, 2026Updated 4 months ago
- ☆10Oct 22, 2026Updated last week
- Continuous Pipelined Speculative Decoding☆22May 25, 2026Updated 5 months ago
- The speculative decoding for uav environment☆17Oct 18, 2025Updated last year
- Models and examples built with hls4ml☆12Apr 8, 2020Updated 6 years ago
- SplitBud is a Split Learning framework built upon Flower☆13Mar 22, 2025Updated last year
- Mini-SGLang is a mini version of SGLang project ().☆13Sep 24, 2025Updated last year
- Some tools for DN42 MeowNetwork☆12Jun 7, 2026Updated 4 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.
- W4A16 MoE GEMM CUDA kernel. Tuned for H200, B200 & B300.☆13Oct 20, 2026Updated last week
- A lightweight CuTe-based CUDA kernel for DuoAttention, optimized for large language model inference.☆12Dec 25, 2025Updated 10 months ago
- Resource Multiplexing in Tuning and Serving Large Language Models (USENIX ATC 2025)☆10Apr 21, 2026Updated 6 months ago
- BlitzScale Router - Distributed LLM Inference Router (Rust)☆17May 25, 2026Updated 5 months ago
- LIFEBENCH: Evaluating Length Instruction Following in Large Language Models☆19Apr 23, 2026Updated 6 months ago
- The open-source project for "Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading"[MobiCom'2022]☆20Aug 4, 2022Updated 4 years ago
- a simple API to use CUPTI☆10Aug 19, 2025Updated last year
- ☆12Nov 21, 2025Updated 11 months ago
- Official implementation of "Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning" (ICLR 2026)☆24Mar 1, 2026Updated 7 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- A simple and naive WPF appliation that launches SSH daemon inside WSL☆10Jun 5, 2019Updated 7 years ago
- Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library☆53Aug 20, 2025Updated last year
- A scheduling framework for multitasking over diverse XPUs, including GPUs, NPUs, ASICs, and FPGAs☆14Jun 17, 2026Updated 4 months ago
- tensorflow fork with Salus integration☆12Jan 7, 2022Updated 4 years ago
- GstShark is a front-end for GStreamer traces☆17Oct 30, 2023Updated 2 years ago
- ☆12May 11, 2025Updated last year
- Modular task agnostic training pipeline using LFM2 from Liquid AI with unsloth.☆17Sep 13, 2025Updated last year