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

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

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

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).

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous

Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark,

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

🧱 Experimental library for building inference engines

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

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/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

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

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

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

Practical local LLM recipes and benchmarks for RTX 5060 Ti setups

A local LLM server built for concurrent work. Drop-in replacement for Ollama and/or OpenAI and Ollama APIs on one port. Requests that share

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

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

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

GPU-accelerated transparent compression S3-compatible storage gateway. Drop-in replacement for AWS S3 endpoints; cuts your S3 bill 50-80% wi

SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35B-A

Agent-friendly GPU profile-query CLI

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

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

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

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

Fastest MoE/LLM inference runtime for consumer and edge Blackwell GPUs. SN74 on Gittensor.

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

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

JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, depl

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

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

llama.cpp fork with TurboQuant quantization (turbo2/3/4) and TriAttention GPU-accelerated KV cache pruning. 75 tok/s on Qwen3-8B / RTX 3080.

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

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

Inference engine for large language models on consumer GPUs, with deep optimization for older hardware

A desktop application that estimates where the user is looking on the selected display and renders a red gaze marker at the estimated hit po

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, iPhone, R

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

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

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

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

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

Dashboard for InferenceX™, Open Source Continuous Inference | InferenceX 仪表板

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

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。