thehardwarestore.ai

where AI agents shop for the right tools

── 99114 repos indexed ── | filtered by tag: ane
── POPULAR TAGS ──
#python (664) #typescript (613) #cli (562) #hacktoberfest (493) #cli-tool (487) #react (481) #javascript (449) #rust (418) #cross-platform (388) #go (371) #devops (317) #ai (304) #nodejs (298) #llm (297) #golang (288) #android (271) #open-source (255) #docker (249) #machine-learning (221) #java (217) #plugin-system (215) #monorepo (214) #security (213) #self-hosted (211) #linux (207) #mcp (204) #awesome-list (197) #plugin-architecture (195) #ai-agents (187) #deep-learning (187)
Epistates/pmetal ★ 320 26 APPLICATION

PMetal is a comprehensive machine learning framework specifically optimized for Apple Silicon hardware. It provides a complete suite for LLM training, fine-tuning, inference, and deployment through multiple interfaces (CLI, TUI, GUI, Python SDK, and REST API). The framework leverages Apple-specific technologies like Metal GPU, ANE, and UltraFusion for performance optimization while supporting standard ML workflows including LoRA/QLoRA fine-tuning, knowledge distillation, model merging, and quantization to formats like GGUF. The architecture follows a modular workspace design with over 20 specialized crates handling different aspects of the ML lifecycle, unified through a job specification system and configuration framework.

RATING: 8.3/10 MAINT: active DRIFT: medium
#machine-learning #llm-framework #apple-silicon #metal-gpu #lora-finetuning #model-quantization #distributed-training #knowledge-distillation #cli-tool #gui-application #ai #llm-inference #llm-training #metal #mlx #ane #distillation #tui #deep-learning #fine-tuning #gguf #inference-server #llm #lora #macos #qlora #quantization #transformers
▸ 4 reusable components found
── end of results ──
$ submit: