MirkoCovizzi/ninfer-rtx5090-mobile
High-performance single-GPU inference for RTX 5090 Mobile.
High-performance single-GPU inference for RTX 5090 Mobile.
Canonical Zephyr LTS documentation
Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks
Public repository of the QuickJS Javascript Engine.
OpenCode plugin for viewing LLM Tokens Per Second (TPS) rates
Fresh builds of llama.cpp with AMD ROCm™ 7 acceleration
DeepSeek 4 Flash local inference engine for Metal and CUDA
Rage Agents Govern the Edge
Experimental implementation of DeepSeek v4 Flash in llama.cpp
Agentic review of Linux Kernel code changes
Firmware SDK enabling any IoT device to connect to Golioth - the Universal Connector for IoT
A non-IP protocol for communication between devices and cloud services
NCS Bare Metal repository
Kernel_modules for MTK Platform
Minimal manifest for building TWRP for devices shipped with Android 10+
Xiaomi Mobile Phone Kernel OpenSource
Godot Engine – Multi-platform 2D and 3D game engine
An OpenGL function pointer loader for Rust
syzkaller is an unsupervised coverage-guided kernel fuzzer
Linux kernel source tree
"Das U-Boot" Source Tree