- United Kingdom
- https://www.alexellis.io/
- @alexellisuk
Sponsors
Highlights
Stars
- All languages
- ABAP
- Arduino
- Assembly
- Batchfile
- BitBake
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Crystal
- Dockerfile
- Eagle
- Elixir
- Elm
- Erlang
- FreeBASIC
- Go
- Go Template
- HCL
- HTML
- Haml
- Haskell
- Java
- JavaScript
- Jinja
- Jsonnet
- Jupyter Notebook
- Just
- Kotlin
- Liquid
- Lua
- Makefile
- Markdown
- Mustache
- Nginx
- Nix
- OCaml
- Objective-C
- PHP
- Perl
- PowerShell
- Processing
- Protocol Buffer
- Puppet
- Python
- R
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Smarty
- Starlark
- Swift
- TeX
- TypeScript
- V
- Vala
- Vim Script 8000
- Visual Basic
- Vue
- XSLT
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Experimental quality tasks for local and hosted AI coding agents
GLM-5.3-Flash NVFP4 on two or four DGX Sparks cabled as a ring, with no switch: the RiNGSiDE serving recipe
A virtio device for sharing one NVIDIA GPU across several VMs, at bare-metal speed.
qwen38-flash-next recipe for tp=2 GB10
DeepSeek-V4.1-Flash-1017 on NVIDIA DGX Sparks with TensorFold + EXL3: TP4 (4 Sparks, 93.6 tok/s, 1M context) and TP2 (2 Sparks, 73 tok/s). Launchers, run records, measured numbers. Older vLLM lanes…
The automated safety engine for Cloud cost optimization. Consize safely rightsizes workloads using guarded rollouts and automated SLI-verified rollbacks ✅
A small, atmospheric Three.js cycling game set on a sunlit coastal road.
RigMark benchmarks local AI the way coding agents actually use it.
GLM-5.3-Flash (FP8) + DFlash2 speculative decoding on 4x NVIDIA DGX Spark / ASUS GX10: vLLM TP4, 256K context, switchless ConnectX-7 ring with patched NCCL
DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks
GLM-5.3-Flash (NVFP4) at TP4 across 4x DGX Spark via a switchless RoCE ring + DFlash2 — reproducible recipe
GLM-5.3-Flash (NVFP4) on 2x NVIDIA DGX Spark - vLLM TP2, 262K context, MTP. World-first deploy recipe: 7 day-0 bugs found and fixed, patched sm121 image, probes and full report.
GLM-5.3 Flash EXL3 for 2-4x DGX Sparks
Low-latency collective transport and distributed LLM serving stack for switchless GB10 clusters.
Switchless 4-DGX-Spark RoCE: 2-hop diagonal relay + tree-skip patches on NCCL 2.30.7 (serves MiniMax-M3 ~24 tok/s switchless)
Review-first terminal diff viewer for agentic coders
A TTS that fits in your CPU (and pocket)
Rust port of NVIDIA NeMo Text Processing for Inverse Text Normalization
Miso TTS is an 8 billion, highly emotive text-to-speech model
The first distributed AGI system. Thousands of autonomous AI agents collaboratively train models, share experiments via P2P gossip, and push breakthroughs here. Fully peer-to-peer. Join from your b…
A minimal LLM-powered zero-day vulnerability scanner by AISLE.
RustFS is an open-source, S3-compatible high-performance object storage system supporting migration and coexistence with other S3-compatible platforms such as MinIO and Ceph.
Python tool for converting files and office documents to Markdown.