FFFF ymwangg (Yanming W.) / Starred · GitHub
[go: up one dir, main page]

Skip to content
View ymwangg's full-sized avatar

Block or report ymwangg

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

🚀 The Architecture of Open Source Applications Volume 1 & 2, 500 Lines or Less, Software Design by Example, Performance of Open Source Applications (PDF)

Python 338 70 Updated Jun 1, 2025

🚀 Efficient implementations for emerging model architectures

Python 6,059 816 Updated Nov 16, 2026

high-performance linear attention kernel library built on TileLang

Python 758 89 Updated Oct 30, 2026

AWS Neuron's extension of TorchTitan that adds AWS Trainium support with TorchNeuron for training generative AI models

Python 17 2 Updated Nov 11, 2026

A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.

Python 1 Updated Aug 28, 2026

NKIPy: Rapid Prototyping on Trainium

Python 30 12 Updated Oct 19, 2026
Python 78 20 Updated Oct 19, 2026

A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.

Python 986 186 Updated Nov 16, 2026
Python 20 6 Updated Oct 1, 2026

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Rust 11,249 1,262 Updated Nov 16, 2026

Every front-end GUI client for ChatGPT, Claude, and other LLMs

4,026 298 Updated Nov 15, 2026

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

Python 5,562 446 Updated Oct 20, 2026

PipeEdge: Pipeline Parallelism for Large-Scale Model Inference on Heterogeneous Edge Devices

Python 44 28 Updated Jan 31, 2024

CUDA Templates and Python DSLs for High-Performance Linear Algebra

C++ 10,734 2,184 Updated Nov 6, 2026

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

Python 5,612 810 Updated Nov 16, 2026

This repository contains integer operators on GPUs for PyTorch.

Python 234 55 Updated Sep 29, 2023

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Python 11,054 1,157 Updated Jul 1, 2024

This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & V…

1,318 76 Updated Mar 9, 2025

The official Meta Llama 3 GitHub site

Python 29,144 3,518 Updated Jan 26, 2025

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

Python 1,177 98 Updated Sep 4, 2024

A framework for few-shot evaluation of language models.

Python 14,487 3,813 Updated Nov 4, 2026

📰 Must-read papers and blogs on Speculative Decoding ⚡️

1,308 87 Updated Jun 27, 2026

FlashInfer: Kernel Library for LLM Serving

Cuda 6,940 1,762 Updated Nov 16, 2026

Measuring Massive Multitask Language Understanding | ICLR 2021

Python 1,626 122 Updated May 28, 2023

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

Python 2,344 311 Updated May 11, 2025

SGLang is a high-performance serving framework for large language models and multimodal models.

Python 38,947 10,538 Updated Nov 16, 2026

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Python 9,001 634 Updated May 3, 2024

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Python 3,667 328 Updated Jul 17, 2025

Numbers every LLM developer should know

4,311 139 Updated Jan 16, 2024

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Python 64,827 11,156 Updated Nov 12, 2025
Next
0