WindChimeRan/speculators
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
Interested in Desktop LLM inference (vllm-metal & DGX-Spark) and speculative decoding.
Repositories
WindChimeRan/ohmytimular
WindChimeRan/SiliconBench
This repository includes code and materials for the paper "SiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktops"
WindChimeRan/whack-a-mole-local-llm
Play whack-a-mole using local llm (vllm-metal or vllm dgx-spark)
WindChimeRan/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
WindChimeRan/WindChimeRan.github.io
WindChimeRan/vllm-metal
Community maintained hardware plugin for vLLM on Apple Silicon
WindChimeRan/pytorch_multi_head_selection_re
BERT + reproduce "Joint entity recognition and relation extraction as a multi-head selection problem" for Chinese and English IE
WindChimeRan/vllm-project.github.io
WindChimeRan/inferrs
A TurboQuant inference server
WindChimeRan/spec-windtunnel
WindChimeRan/deep_code_research
deep research agent for codebase
WindChimeRan/metalstat
Apple Silicon GPU/CPU/Memory monitoring CLI — like gpustat, but for Metal
WindChimeRan/NREPapers2018
This repo covers almost all the papers (35) related to Neural Relation Extraction in ACL, EMNLP, COLING, NAACL, AAAI, IJCAI in 2018.
WindChimeRan/OpenJERE
EMNLP2020 findings paper: Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction
WindChimeRan/NREPapers2019
This repo will cover almost all the papers related to Neural Relation Extraction in ACL, EMNLP, COLING, NAACL, AAAI, IJCAI in 2019.
WindChimeRan/CopyMTL
AAAI20 "CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task Learning"
WindChimeRan/VeloQ
Agent-friendly GPU profile-query CLI
WindChimeRan/hypervibe
One-handed vibe coding using Apple TV Remote, customizable buttons and gestures.
WindChimeRan/claude-dotfiles
WindChimeRan/notes-dgx-spark
WindChimeRan/dotfiles
WindChimeRan/offline_video_vllm
WindChimeRan/lemonade
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
WindChimeRan/mlx
MLX: An array framework for Apple silicon
WindChimeRan/game_flashmemory
WindChimeRan/PrairieLearn
Online problem-driven learning system
WindChimeRan/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
WindChimeRan/exo
Run frontier AI locally.