a platform for monitoring the chip situation

Models and training scripts for "LSTMs for Keyword Spotting with ReRAM-based Compute-In-Memory Architectures" (ISCAS 2021).

Docker image for a self-hosted WhisperLive real-time speech-to-text server, powered by faster-whisper. Provides WebSocket streaming for live audio transcription and an OpenAI-compatible REST API. Supports all Whisper models, VAD, NVIDIA GPU (CUDA) acceleration, offline mode, and multi-arch (amd64, arm64).

A pretty way to compress images

Whisper speech-to-text server installer for Ubuntu, Debian, AlmaLinux, Rocky Linux, CentOS, RHEL and Fedora. OpenAI-compatible transcription and translation APIs powered by faster-whisper. Supports all Whisper models, word-level timestamps, JSON/SRT/VTT output, SSE streaming and offline mode.

Coding assistant is a lightweight llama.cpp wrapper for quantized local SLM deployment

Build, run, and setup scripts for the complete TensorRT-LLM pipeline on RTX A6000 Ada (SM89). Reproducible path from HuggingFace checkpoint to deployable .engine file, with FP16 baseline and FP8 quantization. Companion material to the 4-part blog series on ai-box.eu — in preparation for the NVIDIA TensorRT Edge-LLM ecosystem.

Local GPU inference experiments for NVFP4 quantization and Spark model workflows.

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

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

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

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

⚡ TIMTEH Model Forge — Uncensored, abliterated & reasoning-distilled GGUFs. Forged on 8×H200 SXM5 | 1.1TB VRAM

LLM inference with 7x KV cache compression. Combines llama.cpp (production inference engine) with TurboQuant (KV quantization). Run 131K token context on 16GB VRAM. OpenAI-compatible API server. Supports 100+ model architectures.

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

🎤 Record and transcribe voice dictation on Linux with push-to-talk functionality, injecting text directly into any focused application.

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

vLLM serving stack for Gemma 4 31B on RTX PRO 6000 Blackwell, with FP8 KV cache, MTP speculative decoding, and an async FastAPI logging proxy in front.