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.

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

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

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

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

Practical local LLM recipes and benchmarks for RTX 5060 Ti setups

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

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

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,

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

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

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。

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

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

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

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

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

Implementation of LatentMoE,Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts (Elango et al., NVIDIA 2026) — in Pytorch.

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.

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

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

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

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

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

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

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

Operator-grade GPU monitor for NVIDIA GPUs with native GB10 / DGX Spark coherent UMA support — PSI pressure, clock detection, ConnectX-7 net

Local AI engine in Rust: run GGUF and ONNX models for chat, vision, speech and embeddings on your own GPU, RAM and CPU, with automatic place

Catch local LLMs spilling into the CPU. One run shows GPU placement, prefill, decode, memory, power and a verdict.

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

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

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

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

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

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

Crow — a local AI agent, not a chat box: 30 tools, MCP, memory, skills, goals, subagents, vision, and image generation and editing with Qwen

llama.cpp speculative decoding measured on one RTX 3090, Qwen3.6-35B-A3B UD-Q4_K_XL, commit 3737e4137. Published figures are re-derived from

SpeakCrate: self-hosted text-to-speech API powered by Kokoro. OpenAI-compatible speech endpoint, 50+ voices across 9 languages, streamed aud

Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simula

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

Minimal FlashAttention in CUDA C++/CuTe: readable WMMA/CuTe kernels, no NxN workspace, up to 4.5x faster than naive PyTorch