Tree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port with custom Metal kernels for hybrid model support.
☆145Apr 15, 2026Updated 6 months ago
Alternatives and similar repositories for ddtree-mlx
Users that are interested in ddtree-mlx are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Lossless DFlash speculative decoding for MLX on Apple Silicon☆789Aug 20, 2026Updated last month
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆61Apr 18, 2026Updated 6 months ago
- Exact speculative decoding on Apple Silicon, powered by MLX.☆389Apr 20, 2026Updated 5 months ago
- ☆397Apr 16, 2026Updated 6 months ago
- vLLM Metal plugin powered by mlx-swift — high-performance LLM inference on Apple Silicon☆274Jun 3, 2026Updated 4 months 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.
- Minimalist repo to do mlx vlm constrained decoding in batch mode☆19Apr 11, 2026Updated 6 months ago
- MLX (Apple Silicon) port of MiniMax-H3 — 33B joint video+audio diffusion. Validated against the diffusers reference; AdaLN precompute dro…☆28Oct 8, 2026Updated last week
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,173Aug 18, 2026Updated last month
- 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…☆2,596Oct 10, 2026Updated last week
- Moshi-Finetune-MLX lets you fine-tune Moshi (Native, Real-Time, Speech-to-Speech) models all on Apple Silicon.☆26Apr 21, 2026Updated 5 months ago
- Local AI workstation — discover, run, chat, benchmark, and generate images from open-weight models. DFlash/DDTree speculative decoding, T…☆25Oct 5, 2026Updated last week
- The best benchmark for LLMs on Apple's MLX framework knowledge and coding tasks.☆38Jun 12, 2026Updated 4 months ago
- Tiny evaluation of leading LLMs on competitive programming problems☆14Apr 10, 2026Updated 6 months ago
- JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon☆229Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆38Mar 30, 2026Updated 6 months ago
- MLX Model Quantization Toolkit - Comprehensive collection of Jupyter notebooks for converting and quantizing large language models usi…☆15Aug 16, 2025Updated last year
- ☆15Jun 13, 2025Updated last year
- Implementation for IceCache: Memory-Efficient KV-cache Management for Long-Sequence LLMs (ICLR 2026).☆25Jun 9, 2026Updated 4 months ago
- MMLU-Pro eval results☆15Aug 21, 2025Updated last year
- Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unslot…☆1,443Jun 23, 2026Updated 3 months ago
- Structured Chain-of-Thought☆221May 16, 2026Updated 5 months ago
- Train Large Language Models on MLX.☆434Updated this week
- Train embedding and reranker models for retrieval tasks on Apple Silicon with MLX☆188Sep 18, 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.
- LLM training on Apple's Neural Engine — native Obj-C, private APIs, zero GPU. Dynamic weight pipeline for training without kernel recompi…☆59Mar 17, 2026Updated 7 months ago
- Flash-MoE sidecar slot-bank runtime for large GGUF MoE models on Apple Silicon — llama.cpp fork☆135Oct 7, 2026Updated last week
- ☆17Sep 29, 2026Updated 2 weeks 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
- ☆236Jun 11, 2026Updated 4 months ago
- ☆19Oct 7, 2026Updated last week
- [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference☆344Aug 19, 2026Updated last month
- ☆37Jul 27, 2026Updated 2 months ago
- An intelligent load balancer for LM Studio that distributes requests across multiple loaded language models, optimizing resource utilizat…☆21Oct 13, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆73Updated this week
- Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.☆1,866Jul 2, 2026Updated 3 months ago
- A native Mac App for LLM fine-tuning on Apple Silicon — fully on-device, fully open source.☆279Updated this week
- Simple Implementation of a Transformer in the new framework MLX by Apple☆19Nov 18, 2024Updated last year
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,926Updated this week
- Mixed-vendor GPU inference cluster manager with speculative decoding☆38Jul 2, 2026Updated 3 months ago
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆90Oct 4, 2026Updated 2 weeks ago