Havuz

Black-box LLM distillation for any verifiable task, with text or image inputs: teacher API -> rejection sampling -> SFT -> eval -> GRPO

AnyJev, open LLM’lerden typed kararlar ve eşiklenebilir olasılıklar üretmek için calibration ve karar katmanları sunan bir Python kütüphanesidir.

Neden yükseliyor · Yedi günde 802 yıldız almış; dikkat çekmesinde etiket gerektirmeyen ilk seviye, az etiketle kalibrasyon iddiası ve modeli fine-tune etmeden karar endpoint’i sunma yaklaşımı etkili görünüyor. Bu ilgi benimseme kanıtı değil; verilen sonuçlar README’deki sınırlı benchmark’a dayanıyor.

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine f

ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenC

Spark-X2.5, yerel çalıştırma ve agent iş akışları için tasarlanmış 1.7B ve 4B boyutlarında açık dil modelleri serisidir.

Neden yükseliyor · Yeni model serisi; uzun context, küçük model boyutu ve agent/coding yeteneklerini aynı anda öne çıkarıyor. README'de 34 günlük yaş, 386 yıldız ve son 28 günde 9 commit ile 2 farklı yazar bilgisi var; bunlar erken ilgi ve güncel çalışma gösteriyor, ancak model performansını bağımsız olarak kanıtlamıyor.

Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and how

A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative decodi

Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memo

A small chat model trained from scratch: tokenizer → pretraining → SFT → RL → multimodal. 0.78B params, CORE 0.248, tool calling, vLLM. Weig

Halo is an open-source framework built by White Circle for training large language and multimodal models

Self-hosted Chess.com alternative: Game Review for your Chess.com & Lichess games, play vs Stockfish or a friend, lessons + opening trainer,

Open-source local implementation of MiniMax H3 Context-IR. Turn simple prompts into structured, validated H3 video briefs.

dgx-spark-qwen38 is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Ace

ModelSphere is an open-source LLM inference infrastructure designed to make production-grade model serving simple, efficient, and continuous

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

MCP server that delegates Claude Code agent work to local models (llama.cpp / vLLM) on your own hardware

A MoE inference engine you can read in an afternoon.

A top for local LLMs: memory, paging, GPU and tokens/s for oMLX, Ollama, llama.cpp, vLLM and more

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM i

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Cal

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-awa

An open-source inference engine for AI functions in SQL

Open-source, self-hostable social listening.

Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/a

Real-time hardware and LLM inference monitoring — GPU, CPU, memory, and vLLM metrics streamed to a dashboard.

An open-source, coding agent harness designed specifically for local LLMs. Designed as everything a user needs to jumpstart their own harnes

Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable

Did your change make your LLM server faster? Measure it: faster, slower, or too close to call. Linux and Apple Silicon.

Your AI intranet: network the computers you already own for inference and training.

Privacy-first LLM proxy and AI gateway - load balancing, multi-provider routing, API key management, usage tracking, rate limiting. Self-hos

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

The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLL

The open-source AI platform for enterprises that can't send data to the cloud. OpenAI-compatible API, full management dashboard, zero data e

Legacy: self-hosted LLM/RAG stack installer for DGX Spark (arm64). The work continued as AGmind Systems Lab — measured local-LLM performance

one-year LLM serving trace from Chutes

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,

📚 An educational, step-by-step implementation of LLM KV cache reuse — learn prefix caching, chunk keys, storage & eviction, from pure Python

QwenCleo-ASR is the currently State-Of-The-Art (SOTA) open-source model for Egyptian Arabic & code-switching speech recognition Built on Qwe

Agent and LLM API performance monitoring via network packet probe. Measures performance of OpenClaw, Claude, Codex, DeepAgents and more — de

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression wit

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

Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on

Open source Enterprise AI Gateway for API, MCP and agent, and AI model traffic. One Apache-2.0 binary: 72 native providers behind an OpenAI-

Network-faithful simulation of LLM serving and training deployments

Hemmingway-1: a 27B model that writes the way a person writes. Open weights, free for non-commercial use (CC BY-NC 4.0); commercial use by a

Lightweight proxy for LLM

Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVID

Disaggregated quantization official codebase

A tiered-memory system design for workloads that don't fit in RAM: measure the working set, pin the hot tier, stream the cold tier from flas

croit AIplane — one plane for all your AI. Self-hosted AI infrastructure connecting applications and users with models, agents, tools and en