Lists (1)
Stars
Differentiable Bloch wave simulations for electron diffraction refinement
vLLM fork for Tesla V100 (SM70) with AWQ 4-bit support, CUDA 12.8 build flow, and validated Qwen3.5 27B/35B deployment on multi-GPU V100.
Hand-written NVFP4 W4A16 CUDA kernels and chain-MTP speculative serving — Qwen3.6-27B at up to 366 tok/s on four Tesla V100s, hardware with no FP4 support
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.
Local natural-language-to-shell command generator. A 941 MB fine-tuned Qwen2.5-Coder-1.5B running on CPU in ~1s.
Fast, parallel 2D Delaunay triangulation using exact integer predicates
RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink
The JavaScript / Wasm runtime that powers Cloudflare Workers
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
You like pytorch? You like micrograd? You love tinygrad! ❤️
Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.
A lossless LLM Quantization method using bitpacked index lookups
Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.
Syncing antigravity settings, gemini skills, and GEMINI.md across machines
MOPA laser settings to make colorful oxide layers on stainless steel
Confine an AI agent (Claude Code, Codex, oh-my-pi, ...) to one directory with a BPF-LSM program, and watch it live over eBPF.
Experimental Linux microvm setup with a TypeScript Control Plane as Agent Sandbox
Dr.Jit — A Just-In-Time-Compiler for Differentiable Rendering
Mitsuba 3: A Retargetable Forward and Inverse Renderer
Benchmarks for reading and interpreting mmCIF files