DFlash: Block Diffusion for Flash Speculative Decoding
☆5,573May 10, 2026Updated 2 months ago
Alternatives and similar repositories for dflash
Users that are interested in dflash are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆392Apr 16, 2026Updated 3 months ago
- LLM speculative inference server for consumer hardware & heterogeneous computing☆2,724Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,056Updated this week
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆6,905Jul 9, 2026Updated 3 weeks ago
- TokenSpeed is a speed-of-light LLM inference engine.☆1,824Updated this week
- 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.
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,055Updated this week
- Lossless DFlash speculative decoding for MLX on Apple Silicon☆758Jun 11, 2026Updated last month
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆326Jul 1, 2026Updated last month
- Exact speculative decoding on Apple Silicon, powered by MLX.☆382Apr 20, 2026Updated 3 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆31,488Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,499Feb 20, 2026Updated 5 months ago
- Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, GLM and other models.☆69,683Updated this week
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆704Updated this week
- Official implementation of “Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding”.☆128Jul 25, 2026Updated 2 weeks ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A lightweight inference engine supporting speculative speculative decoding (SSD).☆982May 10, 2026Updated 2 months ago
- high-performance linear attention kernel library built on TileLang☆627Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,127Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆88,441Updated this week
- slime is an LLM post-training framework for RL Scaling.☆7,801Updated this week
- A vector index built on TurboQuant, written in Rust with Python bindings☆14,662Updated this week
- MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.☆5,304Updated this week
- Tree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port wi…☆145Apr 15, 2026Updated 3 months ago
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,184Jul 30, 2026Updated last week
- 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.
- Nano vLLM☆14,894Apr 26, 2026Updated 3 months ago
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆4,696May 17, 2026Updated 2 months ago
- Official inference framework for 1-bit LLMs☆39,814Jul 27, 2026Updated last week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,628Updated this week
- ~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - …☆8,856Updated this week
- Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.☆13,626Jul 24, 2026Updated 2 weeks ago
- A framework for efficient model inference with omni-modality models☆5,932Updated this week
- ☆7,002Jul 20, 2026Updated 2 weeks ago
- 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG☆35,064Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer☆8,718Updated this week
- JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Causal Parallel Tree Drafting☆175Jul 31, 2026Updated last week
- A kernel library written in tilelang☆1,707Apr 23, 2026Updated 3 months ago
- KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44…☆1,042Apr 23, 2026Updated 3 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,150Updated this week
- 🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models☆10,720Jul 30, 2026Updated last week
- dLLM: Simple Diffusion Language Modeling☆2,664Jul 17, 2026Updated 3 weeks ago