2-day current streak·52-day longest streak
-
turboquant_plus ★ PINNED
No description.
Python ★ 7.0k 11d agoExplain → -
longctx ★ PINNED
Open long-context inference stack: retrieval + open weights, no closed parts. pip install longctx.
Python ★ 7 1mo agoExplain → -
llama-cpp-turboquant ★ PINNED ⑂
LLM inference in C/C++
C++ ★ 1.9k 2d agoExplain → -
elm327_obd_for_mac ★ PINNED
I'm crazy and trying to make a ForScan OBD reader work on my mac.
Rust ★ 11 3mo agoExplain → -
vllm-swift ★ PINNED
vLLM Metal plugin powered by mlx-swift — high-performance LLM inference on Apple Silicon
Python ★ 269 20d agoExplain → -
usbinfo ★ PINNED ⑂
No description.
★ 0 5y agoExplain → -
vllm-turboquant ⑂
A high-throughput and memory-efficient inference and serving engine for LLMs
Python ★ 6 1mo agoExplain → -
mlx ⑂
MLX: An array framework for Apple silicon
★ 5 1mo agoExplain → -
momento
Deterministic State Recovery for AI Coding Agents
Python ★ 5 3mo agoExplain → -
pascal-egpu
Driverless NVIDIA Pascal (GTX 1060) compute from macOS Apple Silicon over Thunderbolt eGPU
Python ★ 4 2mo agoExplain → -
BookTies
The new Book Ties!!
★ 4Explain → -
obsidian-link-range ⑂
Add ranged link support to Obsidian
★ 4 4mo agoExplain → -
pastors-pocket-spurgeon
Offline Spurgeon study companion — pastoral counsel, sermon prep, and Sword & Trowel sermon grading. Gemma-4-12B fine-tune served on TurboQuant llama.cpp.
Python ★ 3 7d agoExplain → -
BookTiesOld
Book Ties old source code.
★ 3 15y agoExplain → -
cs161
StemVille real-time data plotting experiment
JavaScript ★ 2 15y agoExplain → -
main_web
No description.
★ 2 15y agoExplain → -
LearnPerl
just perl code
★ 2Explain → -
ffai
FFAI — F*cking Fast AI. Dual-engine inference: Swift (Apple/iPhone, native Metal) + Rust (cross-platform: CUDA/Vulkan/ROCm). Shared kernels via metaltile.
Swift ★ 1 15d agoExplain → -
metaltile ⑂
A Rust-embedded DSL for writing Apple Metal GPU kernels. Write tile-level algorithms in Rust, get optimized Metal Shading Language out.
Metal ★ 1 15d agoExplain → -
ds4-turboquant_plus
Private backup of TQ+ Metal port work on antirez/ds4. Branch tom/turbo3-kv-cuda (turbo2/3/4 + Wave M3 inline-dequant + half-tile + CUDA stubs + h8 Flash WIP).
C ★ 1 29d agoExplain → -
tqkit
Unified toolkit for benchmarking and integrating TurboQuant+ KV-cache compression across llama.cpp, vLLM, MLX, and vllm-swift.
Python ★ 1 1mo agoExplain → -
mlx-swift ⑂
Swift API for MLX
★ 1 1mo agoExplain → -
mlx-swift-lm ⑂
LLMs and VLMs with MLX Swift
Swift ★ 1 11d agoExplain → -
vllm-metal ⑂
Community maintained hardware plugin for vLLM on Apple Silicon
★ 1 2mo agoExplain → -
turboquant-tinygrad-bridge ⑂
Compressed KV cache as cross-backend wire format for Metal + CUDA split inference over Thunderbolt 5
★ 1 2mo agoExplain → -
agent-view ⑂
No description.
★ 1 4mo agoExplain → -
zero
No description.
Rust ★ 0 10d agoExplain → -
ds4 ⑂
DeepSeek 4 Flash local inference engine for Metal and CUDA
★ 0 27d agoExplain → -
atlas ⑂
Pure Rust Inference Engine
★ 0 13d agoExplain → -
homebrew-tap
Homebrew tap for TheTom projects (vllm-swift)
Ruby ★ 0 1mo agoExplain → -
llama.cpp-turboquant-hip ⑂
TurboQuant KV cache compression for llama.cpp — HIP/ROCm port for AMD RDNA3 (gfx1100)
★ 0 1mo agoExplain → -
mlx-c ⑂
C API for MLX
★ 0 2mo agoExplain → -
mlx-lm ⑂
Run LLMs with MLX
★ 0 9d agoExplain → -
clearcode_flutter
No description.
★ 0 3mo agoExplain → -
my-bible-obsidian-plugin ⑂
Your own customization bible in your personal vault!
TypeScript ★ 0 3mo agoExplain → -
QuestMemory
WOW TBC - Quest tracking tool for multi-chars
Lua ★ 0 5mo agoExplain → -
SimpleCraftingProfit
Wow addon for TBC expansion - quick profit checks
Lua ★ 0 5mo agoExplain → -
test-repo-1740104599984
No description.
★ 0 1y agoExplain → -
test-repo-1740104442452
No description.
★ 0 1y agoExplain →
No repos match these filters.