iamwavecut
Follow
-
tdesktop Public
Forked from forkgram/tdesktopFork of Telegram Desktop messaging app.
C++ GNU General Public License v3.0 UpdatedSep 1, 2026 -
warp Public
Forked from warpdotdev/warpWarp is an agentic development environment, born out of the terminal.
-
-
-
audio.cpp Public
Forked from 0xShug0/audio.cppAn all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python depend…
C++ Other UpdatedAug 28, 2026 -
privacy-filter.cpp Public
Forked from localai-org/privacy-filter.cppOpenAI's privacy filter NER model architecture implemented in a minimal C++/GGML runtime
C++ MIT License UpdatedAug 28, 2026 -
ninfer-3090 Public
Forked from Don-Chad/ninfer-3090Fast Qwen3.8-27B inference on one RTX 3090: ReplaySSM, MTP3, reasoning effort, C1-C8 batching, and native Windows and Linux builds.
C++ Apache License 2.0 UpdatedAug 28, 2026 -
cmake_helpers Public
Forked from desktop-app/cmake_helpersCMake helper scripts.
CMake UpdatedAug 28, 2026 -
-
lib_base Public
Forked from desktop-app/lib_baseDifferent useful utilities.
C++ UpdatedAug 28, 2026 -
-
-
mlx-maple-cuda-kernels Public
Exact-output MLX CUDA port of Maple's Metal kernels, with sm86-sm120 profiles and benchmarks
-
ds4 Public
Forked from antirez/ds4DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
C MIT License UpdatedAug 13, 2026 -
-
Best-effort TurboQuant Gemma 4 MTP llama.cpp integration
-
ComfyUI-OrbitQuant Public
ComfyUI nodes for loading universal and model-specific OrbitQuant transformer artifacts
-
OrbitQuant Public
Calibration-free OrbitQuant for transformer backbones, with Hugging Face integration and packed CUDA/Metal inference
-
lingbot-video Public
Forked from Robbyant/lingbot-videoScaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
Python Apache License 2.0 UpdatedJul 31, 2026 -
gopenrouter Public
An unofficial simple OpenRouter client in Go
-
Manifold Public
A self-hosted knowledge and memory layer for AI agents.
-
-
-
llama-cpp-turboquant Public
Forked from TheTom/llama-cpp-turboquantLLM inference in C/C++
C++ MIT License UpdatedJul 15, 2026 -
llama-cpp-turboquant-gemma4 Public
Forked from test1111111111111112/llama-cpp-turboquant-gemma4TurboQuant llama.cpp fork with optimized turbo4 kernels for Gemma 4 D=256/512 heads — lazy K/V, batch decode, warp-cooperative write. 120 t/s with 3.8x KV compression on RTX 3090.
-
seasond Public
A GOPROXY-compatible age gate for public Go module versions.
Go MIT License UpdatedJul 14, 2026 -
telegram-bot-api Public
Forked from OvyFlash/telegram-bot-apiGolang bindings for the Telegram Bot API
Go MIT License UpdatedJul 14, 2026 -
openai-go Public
Forked from openai/openai-goThe official Go library for the OpenAI API
Go Apache License 2.0 UpdatedJul 14, 2026 -
llama-cpp-triattention Public
llama.cpp fork with TurboQuant quantization (turbo2/3/4) and TriAttention GPU-accelerated KV cache pruning. 75 tok/s on Qwen3-8B / RTX 3080.
-