-
VMware
- Tokyo
-
15:37
(UTC +09:00) - https://ik.am
- @making
Stars
- All languages
- ApacheConf
- Batchfile
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Common Lisp
- Cuda
- Dockerfile
- Emacs Lisp
- F#
- Fortran
- Go
- Groovy
- HCL
- HTML
- Java
- JavaScript
- Jupyter Notebook
- Kotlin
- Less
- Lua
- MDX
- Makefile
- Markdown
- Mustache
- Objective-C
- PHP
- Perl
- PowerShell
- Python
- Rich Text Format
- Ruby
- Rust
- Scala
- Shell
- Smarty
- Swift
- TSQL
- TeX
- TypeScript
- Zig
Open-source MCP server that gives AI agents web search (SearXNG) and clean Markdown crawling of pages, whole sites and logged-in areas. Self-hosted, no API key. Firecrawl-compatible API planned.
DeepSeek-V4.1-Flash-1017 on 4 DGX Sparks with TensorFold, switchless support
Reproducible Docker/vLLM deployment, tuning, and benchmarks for DeepSeek V4.1 Flash on a switchless three-node or four-node DGX Spark fabric.
MiniMax-M3.1-Flash on 4x NVIDIA DGX Spark (GB10), vLLM TP4 over RoCE with DSpark: sparkDash prose c1 39.7 tok/s
Import .sql files into TypeScript with full type inference and zero codegen.
A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
A from-scratch CUDA inference engine for 1-6 DGX Sparks (GB10): GLM-5.3, GLM-5.3-Flash and DeepSeek-V4.1-Flash
A dashboard for a home cluster of NVIDIA GB10 (DGX Spark / ASUS GX10) inference servers: GPU and system health, plus live per-model metrics from llama.cpp, vLLM, TensorFold, and SGLang.
Agentic AI security scanner that hunts exploitable vulnerabilities like an adversary, proves them with executable PoCs, and fixes them test-first. A maintained fork of Capital One's VulnHunter, reb…
GLM-5.3 Flash EXL3 for 2-4x DGX Sparks
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
Qwen3.8-Flash-Next on ONE DGX Spark (TP=1)
A JIT Compiler and Runtime for Java in Common Lisp
A unified Java API for executing WebAssembly across multiple runtimes (Wasmtime, WAMR, GraalWasm, Chicory) — write once, swap engines without changing code.
Pinned one-DGX-Spark Docker recipe for DeepSeek V4 Flash with EXL3, SparkInfer, and 262K NVFP4 MLA KV cache
Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support
Missiles and high-tech explosives: Calclavia's work continued.
LWLGL é uma biblioteca modular em Common Lisp para programação de baixo nível voltada a jogos, gráficos, áudio, computação e integração nativa, no espírito do LWJGL.
Real-time Kubernetes dashboard for SREs — live cluster state, drain wizard, YAML editor, just-in-time exec access, cost analysis, and AI diagnosis in a single binary
Docker configuration for running VLLM on dual DGX Sparks
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
GemFire NoSQL database examples applications and API components.
Run Qwen3.5-35B-A3B with llama.cpp and openclaw on NVIDIA DGX Spark (GB10)
Hundreds of models & providers. One command to find what runs on your hardware.
Claude Code skill for migrating Spring Boot 3.x to 4.x and staying current across 4.x minor versions