8000 kilork (Alexander Korolev) / Starred · GitHub
[go: up one dir, main page]

Skip to content
View kilork's full-sized avatar
🦀
Relaxing
🦀
Relaxing

Block or report kilork

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Incremental rust builds up to 92x faster than cargo/rustc. Backed by Y Combinator (F26).

Rust 2,445 94 Updated Nov 19, 2026

Offline NVIDIA Blackwell VBIOS editor.

Python 212 18 Updated Nov 18, 2026

Load a modified VBIOS per NVIDIA GPU at boot on Linux, in memory, through the open kernel modules

Python 78 14 Updated Nov 7, 2026

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per re…

Python 35,783 3,207 Updated Nov 21, 2026

A very-low-resource API-compatible replacement for Ray

Rust 13 1 Updated Nov 1, 2026

GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.

Python 96 13 Updated Nov 6, 2026

Run GLM-5.3 (744B), DeepSeek-V4.1-Flash (748B), MiniMax-M3.1-Flash (428B), GLM-5.3-Flash (321B) and Hy4-Flash (220B) on your own GPUs - from 8 GB of VRAM, NVIDIA and AMD, one dashboard, OpenAI- and…

Cuda 3,157 446 Updated Nov 21, 2026

Reverse engineer anything with agents, from app behavior down to native binaries.

TypeScript 472,734 115,385 Updated Nov 21, 2026

NVIDIA's CUDA platform for Rust. Host runtime crates plus Tile (cutile-rs) and SIMT (cuda-oxide) kernel programming models in idiomatic Rust.

Rust 4,079 379 Updated Nov 21, 2026

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Python 5,904 907 Updated Nov 21, 2026

High-performance single-GPU inference for selected model checkpoints and GPUs.

C++ 3,395 731 Updated Nov 18, 2026

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

C++ 46,553 5,188 Updated Nov 21, 2026

LLM Inference Engine for Metal, CUDA and Vulkan.

Zig 2,366 553 Updated Nov 21, 2026

MIT-licensed fork of PrimeVue. 80+ Vue 3 UI components, Nuxt support and one-command migration.

Vue 451 12 Updated Nov 20, 2026

MiMo-V2.6-Pro-RL on 8 x DGX Spark

Python 8 1 Updated Sep 24, 2026

Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.

JavaScript 98,574 6,734 Updated Nov 21, 2026

Low-latency collective transport and distributed LLM serving stack for switchless GB10 clusters.

Python 106 25 Updated Nov 21, 2026

"O(log N) MoE Expert routing via RT Core ray tracing. BVH traversal replaces matrix multiplication in neural language models."

Python 84 8 Updated Apr 13, 2026

Educational reference: NVIDIA Blackwell SM100 vs SM120, NVFP4, tcgen05, MoE inference on consumer Blackwell

29 5 Updated Sep 3, 2026

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Rust 22,870 2,530 Updated Nov 21, 2026

A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.

C 52,695 6,382 Updated Nov 21, 2026

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

C++ 7,101 1,513 Updated Nov 21, 2026

Agent skills synthesizing years of software engineering discipline into a prescriptive methodology for solo developers

Shell 293 23 Updated Nov 9, 2026

Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package

Rust 347 146 Updated Nov 19, 2026

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

Python 7,324 703 Updated Jul 9, 2026

AI inference, packed simply. A blazing-fast, zero-dependency WebGPU runtime to run GGUF models directly in the browser. Features a symmetric API for seamless local execution and cloud provider rout…

Rust 125 18 Updated Nov 11, 2026

Tile primitives for speedy kernels

Cuda 3,805 350 Updated Sep 12, 2026

A high-throughput and memory-efficient inference and serving engine for LLMs

Python 2 2 Updated Jun 23, 2026
Next
0