Açık kaynak radarı

Havuz

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

149

repo · sayfa 2 / 3

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 inference

51
swellweb/reame 114
CPU-first LLM inference server on llama.cpp. Runs useful models on free-tier ARM boxes; rewriting the input made it ~6x faster and more accu
0,9/gün ort. +0 son gün 1 commit 1 yazar C++ 06 Tem 2026 güncellendi 24 gün önce
cpu gguf inference kv-cache llama-cpp llm openai-api speculative-decoding
114
52
juxhinr/bindwidth 112
Evidence-aware on-prem LLM inference sizing and TCO calculator
1,2/gün ort. +0 son gün 0 commit 0 yazar JavaScript 01 Ağu 2026 güncellendi 02 Ağu 2026
ai calculator inference javascript llm on-prem sizing tco
112
53
Freim32/vllmops 101
Self-hosted vLLM made simple. Git-friendly YAML for models and profiles, full lifecycle from an intuitive CLI and TUI.
0,7/gün ort. +0 son gün — commit Python 18 Haz 2026 güncellendi 02 Eki 2026
cli gpu inference llm local-llm mlops model-serving nvidia
101
54
FedericoTs/quantprobe 93
Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts speed + memory fit for any GGU
0,9/gün ort. +0 son gün 0 commit 0 yazar Python 21 Tem 2026 güncellendi 29 gün önce
benchmark gguf hardware-detection inference llama-cpp llm local-llm moe
93
55
aw3703/batchin-public 89
⚡ Ultra-Reliable AI Inference Gateway & Verifiable Agent Control Plane. Dual-Dispatch, Zero-Token JSON Auto-Healer, VaaS On-Chain Attestatio
0,5/gün ort. +0 son gün — commit Python 26 May 2026 güncellendi 3 gün önce
ai mcp sdk batchin developer-tools integration agent ai-gateway
89
56
ddickmann/vllm-factory 87
Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment
0,4/gün ort. +0 son gün — commit Python 24 Mar 2026 güncellendi 06 Tem 2026
ai-infrastructure colbert colpali embeddings encoder gliner inference ml-infra-deployments
87
57
FastCrest/tether 86
FastCrest Tether: the OSS edge-to-cloud AI deploy CLI. Optimize, verify, deploy across Jetson, RTX, Apple Silicon, AMD. Hybrid edge-cloud in
0,4/gün ort. +0 son gün — commit Python 13 Nis 2026 güncellendi 4 gün önce
cli deployment edge-ai groot inference jetson onnx pi0
86
58
Hal0ai/hal0 85
Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI + sy
0,5/gün ort. +0 son gün 554 commit 1 yazar Python 15 May 2026 güncellendi bugün
ai amd-ryzen-ai fastapi homelab igpu inference llama-cpp llm
85
59
rwilliamspbg-ops/Ghostlink 84
Distributed LLM inference fabric for heterogeneous local clusters. Features zero-copy SPSC ring buffers, automated tuning, and an OpenAI-com
0,6/gün ort. +0 son gün 234 commit 2 yazar Rust 19 Haz 2026 güncellendi dün
af-xdp computer-networks deep-learning distributed-computing gpu-computing inference llm networking-concepts
84
60
helasaoudi/llm-inspector 76
The htop for LLM inference see exactly where every GB of VRAM goes and get measured quantization savings.
0,7/gün ort. +0 son gün 0 commit 0 yazar Python 15 Tem 2026 güncellendi 28 Eyl 2026
gpu-monitoring htop inference llm llm-inference memory-profiler ollama pip
76
61
kikoncuo/jevfire 76
JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.
1,5/gün ort. +0 son gün — commit JavaScript 16 Eyl 2026 güncellendi 18 Eyl 2026
cuda game-ai inference jev llm parallel-decoding structured-output vllm
76
62
maximecb/bebelm 71
CPU-only, pure-Rust implementation of LiquidAI's LFM2.5-8B-A1B LLM
0,5/gün ort. +0 son gün — commit Rust 04 Haz 2026 güncellendi 16 Haz 2026
cpu inference llm local-ai local-llm rust
71
63
mukel/gemma4.java 70
Fast Gemma 4 inference in pure Java
0,3/gün ort. +0 son gün — commit Java 04 Nis 2026 güncellendi 24 Nis 2026
chatgpt gemma gemma4 graalvm inference java jvm llm
70
64
aws-samples/sample-amazon-bedrock-for-beginners 60
Code samples for building AI applications on AWS with Amazon Bedrock, including Converse API, tool use, RAG with Knowledge Bases, guardrails
0,3/gün ort. +0 son gün — commit Python 14 Nis 2026 güncellendi 15 Tem 2026
ai ai-agents aws bedrock guardrails inference rag
60
65
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 — commit Python 20 May 2026 güncellendi dün
arm64 cuda dgx-spark docker gb10 inference llm nvidia
60
66
jitllm/jitllm 58
Smart inference engine that adapts to your hardware to run models faster, even when they don’t fit in memory
1/gün ort. +0 son gün — commit Go 08 Eyl 2026 güncellendi 10 gün önce
cuda inference inference-acceleration inference-engine inference-server jit llm vulkan
58
67
arizqi/cpubrrr 57
Frontier-class LLM inference on a laptop CPU — gpt-oss:20b at ~110 tok/s on Apple M4 Max, 7.5x llama.cpp, no GPU. From-scratch NEON/SME kern
0,5/gün ort. +0 son gün — commit Rust 04 Tem 2026 güncellendi 11 Ağu 2026
apple-silicon cpu gpt-oss inference llm mixture-of-experts neon quantization
57
68
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 — commit C++ 08 Nis 2026 güncellendi 02 Tem 2026
cuda ggml inference kv-cache llama-cpp llm quantization turboquant
57
69
lvyufeng/PocketLLM 55
Inference engine for large language models on consumer GPUs, with deep optimization for older hardware
0,3/gün ort. +0 son gün — commit Python 29 Nis 2026 güncellendi 16 gün önce
ascend consumer-gpu cuda deepseek glm inference inference-engine llm
55
70
shifulegend/project-zero 55
CPU-optimized LLM inference engine (C)
0,4/gün ort. +0 son gün — commit C 06 Haz 2026 güncellendi 6 gün önce
avx512 bitnet c99 cpu cpu-inference deepseek gguf inference
55
71
AEON-7/vllm-dflash 53
DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding
0,3/gün ort. +0 son gün — commit Python 13 Nis 2026 güncellendi 06 Eki 2026
blackwell block-diffusion dflash dgx-spark docker inference llm nvfp4
53
72
infercrane/infercrane 53
Open-source infrastructure for the full inference lifecycle: deploy, observe, scale, optimize, and safely release self-hosted models behind
0,6/gün ort. +0 son gün 0 commit 0 yazar Go 09 Ağu 2026 güncellendi 2 gün önce
ai-infrastructure aws gcp golang inference kubernetes llm mlops
53
73
openfabric-systems/simllm 51
Network-faithful simulation of LLM serving and training deployments
0,5/gün ort. +0 son gün 0 commit 0 yazar Python 03 Ağu 2026 güncellendi 28 gün önce
distributed-training inference llm networking rocev2 sglang simulation vllm
51
74
JINO-ROHIT/tachyon 49
a LLM inference engine to run on consumer hardware
0,2/gün ort. +0 son gün — commit Python 14 Mar 2026 güncellendi 15 Nis 2026
inference llm nlp pytorch transformer
49
75
asher/gmlx 47
Local inference platform for K/IQ-quant GGUF models on Apple Silicon
0,4/gün ort. +0 son gün — commit Python 19 Tem 2026 güncellendi dün
anthropic-api apple-silicon gguf gguf-model-support gguf-runner inference inference-engine llm
47
76
back2matching/turboquant 46
First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.
0,2/gün ort. +0 son gün — commit Python 25 Mar 2026 güncellendi 29 gün önce
compression gpu huggingface inference kv-cache llm machine-learning pytorch
46
77
ohdearquant/lattice 46
Run AI models on Apple Silicon and Raspberry Pi
0,3/gün ort. +0 son gün — commit Rust 13 May 2026 güncellendi bugün
apple-silicon embeddings fine-tuning graphdb inference llm local-llm machine-learning
46
78
enescingoz/mac-llm-bench 45
Community benchmark database for running LLMs on Apple Silicon Macs
0,2/gün ort. +0 son gün — commit Shell 05 Nis 2026 güncellendi 23 Nis 2026
apple-silicon benchmark inference llama-cpp llm llm-benchmark local-llm tokens-per-second
45
79
JeremiahM37/strix-halo-sglang 44
SGLang Docker image for AMD Strix Halo (gfx1151 / Radeon 8060S)
0,3/gün ort. +0 son gün — commit Python 13 May 2026 güncellendi 17 Eyl 2026
amd docker gfx1151 inference llm rocm sglang strix-halo
44
80
meshapplied/goethe 44
Serve your models fast on your own infra in 3 steps.
1,6/gün ort. +0 son gün — commit Rust 08 Eki 2026 güncellendi 3 gün önce
gpu inference llm nvfp4 nvidia openai-api self-hosted sglang
44
81
rferrari/boar-app 44
BOAR - Adaptive Local Intelligence
1/gün ort. +0 son gün — commit C 22 Eyl 2026 güncellendi 11 gün önce
ai inference intelligence llm moe offline research
44
82
xigh/herbert-rs 44
Local LLM inference engine written from scratch in Rust — hand-written AVX-512 assembly kernels, Metal & Vulkan compute shaders. Supports Qw
0,2/gün ort. +0 son gün — commit Rust 15 Mar 2026 güncellendi 4 gün önce
gemma ia llm moe opensource openweight qwen inference
44
83
praxis-proxy/ai 41
AI Gateway
0,3/gün ort. +0 son gün — commit Rust 30 Haz 2026 güncellendi dün
agentic ai inference networking proxy rust anthropic anthropic-api
41
84
686f6c61/NaN-Open-WebUI 40
Tu propio "ChatGPT" con todos los modelos de NaN (qwen, deepseek, gemma, mimo, whisper, kokoro), self-hosted en Docker. Pones tu API key y l
0,3/gün ort. +0 son gün — commit HTML 10 Haz 2026 güncellendi 9 gün önce
ai ai-chat chatgpt docker inference llm nan open-webui
40
85
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 — commit Rust 22 May 2026 güncellendi 2 gün önce
asr compiler computer-vision cuda deep-learning inference llm machine-learning
40
86
sauravsingla/MemVanta 40
Low-memory C++20 LLM inference runtime for quantized GGUF models on CPU — mmap-backed weights, paged KV cache, Q4/Q8 kernels, and reproducib
0,5/gün ort. +0 son gün — commit C++ 20 Ağu 2026 güncellendi 4 gün önce
llm llm-inference local-llm benchmarking cpp cpp20 cpu-inference edge-ai
40
87
Atlas-Inf/atlas 37
Atlas Inference is a dependency free lightweight inference engine meant to run LLMs on YOUR compute seamlessly. Supports GB10 and Strix Halo
0,5/gün ort. +0 son gün — commit Rust 24 Ağu 2026 güncellendi bugün
ai inference inference-engine llm
37
88
tsaipifong/whirl-llm 37
WHIRL (Windows HIP Inference for RDNA LLMs): native Windows C++/HIP LLM inference engine for the AMD Ryzen AI Max+ 395 (Radeon 8060S) and Ra
1,1/gün ort. +0 son gün — commit C++ 03 Eki 2026 güncellendi bugün
amd gguf hip inference llm mxfp4 r9700 rdna4
37
89
marzukia/qMLX 36
qMLX: Custom inference engine for Qwen 3.5 122B on Apple Silicon, extending MLX with hybrid attention support, SSD-backed KV cache, and RYS
0,3/gün ort. +0 son gün — commit Python 09 Tem 2026 güncellendi 5 gün önce
apple-silicon hybrid-attention inference kv-cache llm mlx mtp qwen
36
90
ExVRAM/exvram-lab 35
Compute-for-memory research lab for running larger LLMs on memory-constrained consumer GPUs. Official website exvram.pro
0,9/gün ort. +0 son gün — commit Python 26 Eyl 2026 güncellendi 12 gün önce
benchmarking blackwell cuda gpu inference llm local-llm low-bit
35
91
rajveer43/VeloxQuant-MLX 34
Fast KV-cache quantization for Apple Silicon (MLX) — 43 research-adapted compression methods with Metal kernels
0,2/gün ort. +0 son gün — commit Python 19 Nis 2026 güncellendi dün
kv llm mlx quantization kv-cache macos ondeviceai apple-silicon
34
92
RightNow-AI/TIDE 34
Dynamic per-token early exit for LLM inference. Skip layers tokens don't need
0,1/gün ort. +0 son gün — commit Python 17 Mar 2026 güncellendi 18 Eyl 2026
early-exit inference inference-api inference-engine llm optimization transformer
34
93
surya-koritala/condor 34
Qwen3.8-Flash-Next (180B MoE) on one 12-16 GB NVIDIA GPU, Linux or Windows. Own engine, own compression.
1,5/gün ort. +0 son gün — commit Python 14 Eki 2026 güncellendi 15 gün önce
cuda inference linux llm local-llm mixture-of-experts nvidia qwen
34
94
jcartu/rasputin-memory 33
The ultimate memory backend for OpenClaw and Claude Code. Persistent conversation memory with LLM fact extraction, foundation-model rerankin
0,1/gün ort. +0 son gün — commit Python 26 Mar 2026 güncellendi 25 Nis 2026
ai knowledge-graph llm memory nvidia qdrant rag self-hosted
33
95
aivrar/multi-turboquant 30
Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simula
0,1/gün ort. +0 son gün — commit Python 10 Nis 2026 güncellendi 26 gün önce
attention compression cuda deep-learning gpu inference kv-cache llama-cpp
30
96
gdevenyi/huggingface-estimate 30
A web-based memory usage and performance calculator for Huggingface GGUF models
0,1/gün ort. +0 son gün — commit JavaScript 17 Nis 2026 güncellendi 20 Tem 2026
estimate huggingface llama-cpp llamacpp llm memory qwen deepseek
30
97
stfurkan/bitgpu 30
Fast WebGPU runtime for 1-bit (binary-weight) LLMs in the browser. Bit-exact, zero runtime dependencies.
0,2/gün ort. +0 son gün — commit TypeScript 03 Tem 2026 güncellendi 23 Tem 2026
1-bit browser inference llm on-device-ai quantization webgpu
30
98
ariannamethod/notorch 29
neural networks in pure C
0,1/gün ort. +0 son gün — commit C 06 Nis 2026 güncellendi 3 gün önce
diffusion gguf llama llm machinelearning neural-networks termux torch
29
99
Joakimpalm-Zen/xyntetik-runner 29
Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, b
0,2/gün ort. +0 son gün — commit C 10 Tem 2026 güncellendi bugün
c cuda edge-ai gguf inference llm local-llm metal
29
100
MaincodeHQ/from-tin-to-tokens 29
A free textbook on building an LLM inference stack from scratch in Rust.
0,3/gün ort. +0 son gün — commit 13 Ağu 2026 güncellendi 13 Ağu 2026
book gpu inference llm machine-learning rust systems-programming
29