DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous accelerator dispatch.
☆61Apr 18, 2026Updated 6 months ago
Alternatives and similar repositories for mirror-sd
Users that are interested in mirror-sd are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Exact speculative decoding on Apple Silicon, powered by MLX.☆390Apr 20, 2026Updated 6 months ago
- ☆38Mar 30, 2026Updated 6 months ago
- Lossless DFlash speculative decoding for MLX on Apple Silicon☆789Aug 20, 2026Updated 2 months ago
- Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers☆30May 19, 2026Updated 5 months ago
- Flash-MoE sidecar slot-bank runtime for large GGUF MoE models on Apple Silicon — llama.cpp fork☆135Oct 7, 2026Updated 2 weeks ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- 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 6 months ago
- ☆397Apr 16, 2026Updated 6 months ago
- ANE (Apple Neural Engine) CostModel profiler for CoreML models☆35Apr 9, 2026Updated 6 months ago
- REAP expert pruning for MoE LLMs on Apple Silicon via MLX☆58Mar 16, 2026Updated 7 months ago
- Minimalist repo to do mlx vlm constrained decoding in batch mode☆20Apr 11, 2026Updated 6 months ago
- Running a big model on a small laptop☆58Mar 28, 2026Updated 6 months ago
- Moshi-Finetune-MLX lets you fine-tune Moshi (Native, Real-Time, Speech-to-Speech) models all on Apple Silicon.☆26Apr 21, 2026Updated 6 months ago
- Triton‑style kernel toolkit for MLX plus a small upstream incubator: prototype, benchmark, and upstream fusions for Apple Silicon☆52Mar 31, 2026Updated 6 months ago
- ☆14Nov 27, 2025Updated 10 months 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.
- INVISIX.IO - Corporate-grade privacy solution, out of the box.☆18Aug 27, 2026Updated last month
- The best benchmark for LLMs on Apple's MLX framework knowledge and coding tasks.☆38Jun 12, 2026Updated 4 months ago
- ☆236Jun 11, 2026Updated 4 months ago
- A repo of useful MLX skills.☆90Jan 25, 2026Updated 8 months ago
- An MLX port of Meta's Coconut reasoning model☆16Sep 2, 2025Updated last year
- ⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache…☆786Updated this week
- ☆47Oct 4, 2026Updated 2 weeks ago
- 🔥 The fastest local AI engine for Apple Silicon. Optimised for agentic use.☆99May 24, 2026Updated 4 months ago
- Find the hidden meaning of LLMs☆42Nov 13, 2025Updated 11 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.
- Test LLMs on real tasks. Compare models side-by-side.☆430Aug 10, 2026Updated 2 months ago
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆345Aug 19, 2026Updated 2 months ago
- KAN (Kolmogorov–Arnold Networks) in the MLX framework for Apple Silicon☆32Jun 18, 2025Updated last year
- Sequential Monte Carlo Speculative Decoding☆54Aug 25, 2026Updated last month
- Local AI runtime for training & running small LLMs directly on Apple Neural Engine (ANE). No CoreML. No Metal. Offline, on-device fine-tu…☆130Aug 23, 2026Updated 2 months ago
- Minimal Claude Code alternative powered by MLX☆47Jan 11, 2026Updated 9 months ago
- Run LLMs with MLX☆14May 1, 2026Updated 5 months ago
- The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B…☆2,619Oct 10, 2026Updated last week
- Run transformers directly on Apple's Neural Engine in Swift bypass coreml entirely☆173Sep 12, 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.
- MiniMax H3 (video + audio) on TensorFold 0.6.5 with an H3 family, Mac Studio M5 Ultra: 5 s 864x480 clip in ~50 s, 40 s at 768x448 — the f…☆29Oct 7, 2026Updated 2 weeks ago
- Metal Cuda Direct Memory Access☆201Oct 15, 2026Updated last week
- ☆32May 15, 2026Updated 5 months ago
- Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unslot…☆1,449Jun 23, 2026Updated 4 months ago
- High-performance batched Top-K selection for CPU inference. Up to 80x faster than PyTorch, optimized for LLM sampling with AVX2 SIMD.☆18Mar 20, 2026Updated 7 months ago
- DSPy Forge: A visual tool for building and deploying compound agent programs using DSPy.☆14Nov 4, 2025Updated 11 months ago
- mlx-lm server wrapper for agentic harness☆21Jan 26, 2026Updated 8 months ago