Açık kaynak radarı

Havuz

Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.

repo · sayfa 1 / 1

Sırala

Yıldız/gün (hız)Son gün (★/gün)Son hafta (★/gün)Son ay (★/gün)Toplam yıldız AI önem skoru Bana uyum Commit (28g)Yazar (28g)En yeni

Konu

Tümü AI / LLM18 Veri9 Geliştirici araçları13 Diğer3 SaaS altyapı13 Web11

Süz

Yalnız hareketli Yalnız analizli≥ 0 ≥ 100 ≥ 500 ≥ 2.000

Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.

EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster

Sırala:

Etiketler yükleniyor…

Aktif cuda

1
zhongkaifu/TensorSharp 655
A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interf
3/gün ort. +3 son gün +3,4 son 30g — commit C# 03 Nis 2026 güncellendi bugün
gemma inference inference-engine llm qwen transformers gemma4 gguf
655
2
Tylogi/TyloQuant 95
Get more intelligence from every bit. Better quantization formats and smarter calibration let larger, stronger models run smoothly on the ha
0,9/gün ort. +0 son gün +0,5 son 30g — commit C++ 24 Tem 2026 güncellendi dün
apple-silicon cuda deepseek gemma gguf llm llm-inference llm-quantization
95
3
hwdsl2/self-hosted-ai-stack 174
Deploy a self-hosted AI stack with Docker Compose: local LLMs, chat, document parsing, embeddings, transcription, text-to-speech and MCP too
0,9/gün ort. +1 son gün +0,4 son 30g — commit Shell 05 May 2026 güncellendi 4 gün önce
ai ai-stack docker docker-compose embeddings linux llm local-ai
174
4
giannisanni/pulsar 234
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
2/gün ort. +0 son gün +0,3 son 30g — commit Rust 13 Tem 2026 güncellendi 01 Eyl 2026
cuda gguf glm inference-engine llm local-llm mixture-of-experts moe
234
5
tensormux/kernel-skills 89
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quant
0,4/gün ort. +1 son gün +0,3 son 30g — commit TypeScript 10 Nis 2026 güncellendi 21 Haz 2026
ai-coding cuda gpu-kernels high-performance-computing kernel-optimization llm-agents prompt-engineering quantization
89
6
Entrpi/ds4-on-spark 414
Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark,
2,3/gün ort. +1 son gün +0,2 son 30g — commit Shell 12 May 2026 güncellendi 27 Ağu 2026
benchmark cuda deepseek-v4-flash dgx-spark gb10 gguf inference llm
414
7
gammahazard/locate-anything 170
Sleek, mobile-friendly web UI for NVIDIA LocateAnything-3B — open-vocabulary object detection & grounding on your own GPU, via one docker co
1/gün ort. +0 son gün +0,2 son 30g — commit TypeScript 27 May 2026 güncellendi 11 Eyl 2026
bounding-boxes computer-vision cuda docker fastapi gpu grounding machine-learning
170
8
JustVugg/nanoeuler 127
GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.
0,9/gün ort. +0 son gün +0,2 son 30g — commit Cuda 15 Haz 2026 güncellendi 18 Haz 2026
bpe-tokenizer byte-pair-encoding c cublas cuda deep-learning flashattention from-scratch
127
9
timothystewart6/vllm-gb10 60
Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on
0,4/gün ort. +0 son gün +0,2 son 30g — commit Python 20 May 2026 güncellendi 2 gün önce
arm64 cuda dgx-spark docker gb10 inference llm nvidia
60
10
utensils/mold 57
CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, iPhone, R
0,2/gün ort. +0 son gün +0,2 son 30g — commit Rust 12 Mar 2026 güncellendi 6 gün önce
ai candle cli cuda diffusion-models flux gpu image-generation
57
11
SemiAnalysisAI/InferenceX-app 51
Dashboard for InferenceX™, Open Source Continuous Inference | InferenceX 仪表板
0,2/gün ort. +0 son gün +0,2 son 30g — commit TypeScript 11 Mar 2026 güncellendi bugün
agi amd benchmarking cuda deepseek llm nvidia reactjs
51
12
notwitcheer/llm-bench-rig 47
Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable
0,3/gün ort. +0 son gün +0,2 son 30g — commit Python 27 May 2026 güncellendi 2 gün önce
benchmarking cuda fastapi gguf llama-cpp llm lm-evaluation-harness machine-learning
47
13
MIT-RLX/rlx-models 40
ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu
0,2/gün ort. +0 son gün +0,2 son 30g — commit Rust 22 May 2026 güncellendi 3 gün önce
asr compiler computer-vision cuda deep-learning inference llm machine-learning
40
14
raketenkater/ggrun 283
llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.
1,2/gün ort. +0 son gün +0,1 son 30g — commit Go 11 Mar 2026 güncellendi 2 gün önce
cuda gguf llama-cpp llm metal moe multi-gpu golang
283
15
lucifer1004/VeloQ 131
Agent-friendly GPU profile-query CLI
0,9/gün ort. +0 son gün +0,1 son 30g — commit Rust 05 Haz 2026 güncellendi 05 Eki 2026
cli cuda gpu ncu nsys profiling
131
16
FareedKhan-dev/glm-5.2-in-c 75
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
0,7/gün ort. +0 son gün +0,1 son 30g — commit C 15 Tem 2026 güncellendi 15 Tem 2026
c consumer-hardware cpu-inference cuda deep-learning edge-ai glm inference-engine
75
17
atomicmilkshake/llama-cpp-turboquant 57
llama.cpp fork with TurboQuant quantization (turbo2/3/4) and TriAttention GPU-accelerated KV cache pruning. 75 tok/s on Qwen3-8B / RTX 3080.
0,3/gün ort. +0 son gün +0,1 son 30g — commit C++ 08 Nis 2026 güncellendi 02 Tem 2026
cuda ggml inference kv-cache llama-cpp llm quantization turboquant
57
18
ferrumox/fox 190
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
0,8/gün ort. +0 son gün +0 son 30g — commit Rust 08 Mar 2026 güncellendi 22 Ağu 2026
cuda gguf inference-engine llama-cpp llm local-llm mlx ollama
190
19
Sandermage/sndr_core_engine 133
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
0,7/gün ort. +0 son gün +0 son 30g — commit Python 17 Nis 2026 güncellendi 01 Eki 2026
cuda llm-inference qwen vllm speculative-decoding tool-calling rtx-3090 awq
133
20
PINTO0309/screen-eye-tracking 55
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
0,4/gün ort. +0 son gün +0 son 30g — commit TypeScript 18 Haz 2026 güncellendi 03 Tem 2026
eye-tracking onnx electron python react onnxruntime-web wasm webgpu
55
21
zengxiao-he/tessera 556
From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous
3,6/gün ort. +0 son gün -0,3 son 30g — commit Python 05 Haz 2026 güncellendi 27 gün önce
cuda flash-attention fsdp inference-engine jax knowledge-distillation kv-cache llm
556