Havuz

VoiceStudio, yerel speech modellerini masaüstü uygulamasında voice cloning, text-to-speech, transcription ve video dubbing gibi iş akışlarıyla bir araya getiriyor.

Neden yükseliyor · 171 günde 37.761 yıldıza ulaşması dikkat çekici kullanıcı ilgisine işaret ediyor; kapsamlı yerel voice iş akışları ve ElevenLabs alternatifi olarak konumlanması bu ilgiyi açıklayabilir. Son 28 gündeki 1.505 commit yüksek aktivite gösterse de yalnızca 6 farklı yazar görünmesi, bu hareketin geniş katkıcı tabanına yayıldığını kanıtlamıyor.

Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU

Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.

🧱 Experimental library for building inference engines

Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read text in 30 languages. Patched audio.cpp, local UI in

Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch).

Don't memorize ML. Understand it from first principles including Inference, Cuda, Deep Learning, Data Science and Reinforcement Learning

Uncensored DeepSeek-V4.1-Flash IQ2_XS on Google Colab

Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images

A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interf

Local-first AI video dubbing pipeline: transcription, translation, speech synthesis and timing alignment.

A tool that allows AI to direct the dubbing process, uses the original actor voices and does the audio generation on your local PC

Glyd, model ağırlıklarını ve KV cache'i bit düzeyinde kayıpsız biçimde sıkıştırıp GPU'da kullanmayı hedefleyen bir compression yazılımıdır.

Neden yükseliyor · README, yaygın bir maliyet sorununa doğrudan yanıt verdiğini ve 32B ile 72B modellerde daha az GPU ile çalışmaya dair ölçümler sunuyor; ancak 9 günlük repoda 170 yıldız ve 474 commit'in yalnızca 2 farklı yazardan gelmesi, ilginin ve geliştirme temposunun geniş bir katkıcı tabanına dayandığını göstermiyor. Yükselişin kesin kaynağı veya bağımsız benimsenme verisi bilinmiyor.

llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s

OpenAI-compatible inference server for Qwen3.8 on one RTX 5090 / RTX PRO 6000: the 27B at ~170 tok/s (peaks ~370), Flash-Next (125B MoE) at

Qwen Image 2.1 for DeepSeek Harness: native image editing on Apple Silicon MLX/MFLUX or self-hosted CUDA, LoRA, ControlNet, inpainting, pres

Hybrid GPU + CPU inference for mixture-of-experts models, written in Rust down to the CUDA kernels. A drop-in llama-server.

Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quant k

The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, con

Open-source control panel for the real llama.cpp: see where a model lands in your VRAM before loading, every llama-server flag per model, on

Smart inference engine that adapts to your hardware to run models faster, even when they don’t fit in memory

Evaluating frontier models on real-world ai-infra engineering tasks

Ollama-compatible LLM server on a tuned llama.cpp fork. Beats vllm by 40% on single stream decode, and by 20% on multi stream decode, and be

Compute-for-memory research lab for running larger LLMs on memory-constrained consumer GPUs. Official website exvram.pro

Practical local LLM recipes and benchmarks for RTX 5060 Ti setups

llama.cpp performance patches developed and measured on Tesla P100 (GP100, sm_60). Most are not Pascal-specific.

A realtime assistant for Mac and Windows. Talk to it and it answers aloud, shows your schedule and mail as cards, and hands longer work to a

PantheonSim: GPU simulator for CUDA and ROCm. Run CUDA and HIP programs unmodified on a CPU, no GPU needed: simulated NVIDIA and AMD GPUs fo

Get more intelligence from every bit. Better quantization formats and smarter calibration let larger, stronger models run smoothly on the ha

Run LLMs and Ollama Qwen across AMD XDNA1 NPU, CPU, and GPU on Ryzen AI Linux systems.

Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, b

Deploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings, transcription, text-to-speech and MCP too

为 JAV 日语视频生成日文、中文或双语 SRT 字幕。支持本地音视频识别、时间轴对齐及 API 或本地模型翻译；网页界面操作，视频与音频留在本机。适用于 Windows + NVIDIA 显卡。

AI/LLM on Kubernetes 基础设施知识库：涵盖 GPU、大数据、调度、分布式训练、LLM 推理、RAG、Agent 与生产运维。| AI/LLM on Kubernetes Infrastructure Knowledge Base: Covering GPUs,

[ICML 2026] NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs

ScribeCrate: open-source, self-hosted Whisper speech-to-text server powered by faster-whisper. OpenAI-compatible transcription and English t

Qwen3.8-Flash-Next (180B MoE) on one 12-16 GB NVIDIA GPU, Linux or Windows. Own engine, own compression.

Model Dispatch and Memory Allocator: an LLM inference engine for the hardware you own. Custom CPU, ROCm, Vulkan, CUDA, Metal and Level Zero

Sleek, mobile-friendly web UI for NVIDIA LocateAnything-3B — open-vocabulary object detection & grounding on your own GPU, via one docker co

Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quant

Generate textured, segmented and rigged GLB assets entirely on your own GPU.

Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on

OpenAI-compatible speech serving in Rust: streaming TTS and full-duplex voice over GPT-Live. 128 concurrent PersonaPlex sessions on one GPU.

Durable local inference for Oh My Pi: NInfer + Qwen3.8 27B on one RTX 3090/4090/5090, with restart-resumable OpenAI Responses state.

Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable

ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu

ScribeCrate Live: self-hosted real-time transcription server powered by WhisperLive and faster-whisper. WebSocket transcription and speech-t

🔥 AI agent that ports CUDA code to AMD ROCm using local LLMs — FastAPI + React + Ollama | Live: rocmporter-agent.vercel.app

Unified native AI runtime for Java 17+, Java 22+ (Panama FFM), Android & C++. Run GGUF LLMs, Vision, Video, Whisper ASR, TTS & Embeddings in