Pinned Repositories
batch-processing-gateway
Batch Processing Gateway (BPG)
hiboyang's Repositories
hiboyang/apple-metal-mps-go-mm
Interfacing with Apple Metal-based GPUs
hiboyang/apple-silicon-asitop
Perf monitoring CLI tool for Apple Silicon
hiboyang/Arize-ai-phoenix-AI-observability
AI Observability & Evaluation
hiboyang/build-nanogpt
Video+code lecture on building nanoGPT from scratch
hiboyang/cel-spec
Common Expression Language -- specification and binary representation
hiboyang/chainlit
Build Conversational AI in minutes ⚡️
hiboyang/cni-hero-hands-on
From CNI Zero to CNI Hero: The Hands on tutorial
hiboyang/evals
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
hiboyang/guidance
A guidance language for controlling large language models.
hiboyang/hollance-neural-engine
Everything we actually know about the Apple Neural Engine (ANE)
hiboyang/kubeflow-spark-operator
Kubernetes operator for managing the lifecycle of Apache Spark applications on Kubernetes.
hiboyang/kvproto
Protocol buffer files for TiKV
hiboyang/litestream
Streaming replication for SQLite.
hiboyang/llama3-from-scratch
llama3 implementation one matrix multiplication at a time
hiboyang/LLM-datamllab-LongLM
LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
hiboyang/llm.c
LLM training in simple, raw C/CUDA
hiboyang/lm-evaluation-harness
A framework for few-shot evaluation of language models.
hiboyang/nccl-tests
NCCL Tests
hiboyang/nomiracl
NoMIRACL: A multilingual hallucination evaluation dataset to evaluate LLM robustness in RAG against first-stage retrieval errors on 18 languages.
hiboyang/Python-Package-Template
A easy, reliable, fluid template for python packages complete with docs, testing suites, readme's, github workflows, linting and much much more
hiboyang/qdrant
Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
hiboyang/raft
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
hiboyang/ragas
Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines
hiboyang/recdemo
How to create and record demos in terminal sessions
hiboyang/RemoteShuffleService
Remote shuffle service for Apache Spark to store shuffle data on remote servers.
hiboyang/sglang
SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
hiboyang/spark
Apache Spark - A unified analytics engine for large-scale data processing
hiboyang/spark-connect-go
Apache Spark Connect Client for Golang
hiboyang/sqlglot
Python SQL Parser and Transpiler
hiboyang/trulens
Evaluation and Tracking for LLM Experiments