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 kv-cache

1
zengxiao-he/tessera 555
From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous
3,7/gün ort. +0 son gün — commit Python 05 Haz 2026 güncellendi 25 gün önce
cuda flash-attention fsdp inference-engine jax knowledge-distillation kv-cache llm
555
2
huawei-csl/KVarN 515
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Cal
3,2/gün ort. +0 son gün — commit Python 29 May 2026 güncellendi 22 Haz 2026
agentic-ai kv-cache long-context quantization vllm llm llm-inference
515
3
quantumaikr/quant.cpp 405
LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.
1,8/gün ort. +0 son gün — commit C 28 Mar 2026 güncellendi 26 Nis 2026
delta-compression embeddable gguf kv-cache llm llm-inference pure-c quantization
405
4
Tele-AI/Fluxon 126
An AI-native distributed data plane built in Rust that supports high performance RPC, KV Cache, Message Queue, and File & Object Acceleratio
0,9/gün ort. +0 son gün — commit Rust 12 Haz 2026 güncellendi 6 gün önce
ai-native memory-pool message-queue nosql rpc mooncake distributed-cache inference
126
5
arozanov/turboquant-mlx 114
TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.
0,5/gün ort. +0 son gün — commit Python 28 Mar 2026 güncellendi 30 Nis 2026
apple-silicon kv-cache llm metal mlx quantization turboquant
114
6
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 — commit C++ 06 Tem 2026 güncellendi 23 gün önce
cpu gguf inference kv-cache llama-cpp llm openai-api speculative-decoding
114
7
manjunathshiva/turboquant-mlx 91
Extreme weight + KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant)
0,4/gün ort. +0 son gün — commit Python 06 Nis 2026 güncellendi 4 gün önce
apple-silicon kv-cache llm mlx quantization turboquant
91
8
OnlyTerp/turboquant 86
First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression wit
0,4/gün ort. +0 son gün — commit Python 25 Mar 2026 güncellendi 25 May 2026
attention compression deep-learning google-research iclr kv-cache kv-cache-compression llm
86
9
TheToughCrane/nano-kvllm 75
This project aims to provide a high effective KV cache manage framework for llm inference and improve memory utilization and inference speed
0,3/gün ort. +0 son gün — commit Python 08 Mar 2026 güncellendi 24 Nis 2026
aiinfrastructure kv-cache llm llm-inference vllm
75
10
choihyunsus/soul 67
Soul: The Persistent Memory Layer for Multi-Agent Systems. High-performance session orchestration with SQLite-based KV-Cache for MCP. Give y
0,3/gün ort. +0 son gün — commit TypeScript 08 Mar 2026 güncellendi 5 gün önce
ai-brain kv-cache mcp multi-agent orchestration persistent-memory session-management
67
11
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
12
AttemorySystem/attemory 57
Semantic retrieval for AI agents: high-recall memory and code search that cuts coding-agent token usage by nearly 50%
0,4/gün ort. +0 son gün — commit C++ 15 Haz 2026 güncellendi 13 Ağu 2026
ai-agents attention code-search kv-cache llm local-ai memory memory-retrieval
57
13
Alberto-Codes/turboquant-vllm 51
TurboQuant KV cache compression plugin for vLLM — asymmetric K/V, 8 models validated, consumer GPUs
0,2/gün ort. +0 son gün — commit Python 26 Mar 2026 güncellendi 10 Nis 2026
compression consumer-gpu inference-optimization kv-cache llm quantization transformer triton
51
14
helgklaizar/turboquant-mlx 50
TurboQuant MLX: Flagship high-performance model quantization for Apple Silicon. Squeeze maximum inference speed and memory efficiency out of
0,2/gün ort. +0 son gün — commit Python 25 Mar 2026 güncellendi 05 Ağu 2026
apple-silicon kv-cache llm mlx quantization core metal optimization
50
15
anthony-chaudhary/fak 46
Agentic Runtime
0,3/gün ort. +1 son gün — commit Go 21 Haz 2026 güncellendi bugün
agentic-ai ai-agents golang kv-cache llm-agents llm-inference llm-serving mcp
46
16
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 28 gün önce
compression gpu huggingface inference kv-cache llm machine-learning pytorch
46
17
tanavc1/local-llm-autotune 39
Zero-config local LLM optimization for Ollama, LM Studio, and Apple Silicon MLX. Reduces TTFT by 40%, wall time for local agents by 46%, and
0,2/gün ort. +0 son gün — commit Python 20 Mar 2026 güncellendi 9 gün önce
apple-silicon cli inference-optimization kv-cache llm lm-studio local-ai local-llm
39
18
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 4 gün önce
apple-silicon hybrid-attention inference kv-cache llm mlx mtp qwen
36
19
Tenosra/Proxima 26
Proxima lets existing GPUs serve 4x more concurrent requests
0,3/gün ort. +0 son gün — commit Python 01 Ağu 2026 güncellendi 19 Ağu 2026
kv-cache llm llm-inference llmops mlops vllm vllm-plugins vllm-serve
26
20
jiahongsigma/Efficient-LLM-Inference-Serving-Systems 25
Why is LLM inference slow — and how do you make it fast? A hands-on, first-principles course: roofline → KV cache → quantization → paralleli
0,2/gün ort. +0 son gün — commit Python 30 Haz 2026 güncellendi 11 Ağu 2026
cuda deep-learning flash-attention gpu inference-optimization kv-cache llm llm-inference
25