Zhiqiang Xie

Coauthor of SGLang

Starred Projects (49)

miles by radixark

Enterprise RL for large-scale MoE models

wsxiaoys:

Ying1123:

lewtun:

ekzhang:

Created 3 months ago

Updated 1 day ago

supermemory by supermemoryai

Second brain for LLMs, providing contextual knowledge

tobi:

omarsar:

didierrlopes:

transitive-bullshit:

Created 1 year ago

Updated 23 hours ago

SpecForge by sgl-project

Train speculative decoding models for faster inference

merrymercy:

Ying1123:

zhyncs:

Created 7 months ago

Updated 14 hours ago

MemOS by MemTensor

LLM operating system with long-term memory

luiscape:

xiaofan-luan:

Created 6 months ago

Updated 1 day ago

KernelBench by ScalingIntelligence

Benchmark for LLMs generating GPU kernels from PyTorch ops

luiscape:

chiphuyen:

aksh-at:

Created 1 year ago

Updated 2 days ago

openevolve by algorithmicsuperintelligence

Coding agent for scientific/algorithmic discovery, based on AlphaEvolve paper

chiphuyen:

vincentweisser:

taranjeet:

suquark:

Created 8 months ago

Updated 2 weeks ago

LaCT by a1600012888

Test-Time Training framework for adaptable models

pgarbacki:

Created 7 months ago

Updated 6 days ago

letta by letta-ai

Agent framework for stateful agents with memory, reasoning, and context management

hiyouga:

joewalnes:

c4pt0r:

sxyu:

Created 2 years ago

Updated 1 week ago

SkyRL by NovaSky-AI

RL training pipeline for multi-turn tool use LLMs, optimized for real-world tasks

lewtun:

hiyouga:

WoosukKwon:

zhuohan123:

Created 8 months ago

Updated 1 day ago

mem0 by mem0ai

AI agent memory layer for personalized interactions

anurag:

amin3141:

gregpr07:

marcklingen:

Created 2 years ago

Updated 1 day ago

tokasaurus by ScalingIntelligence

LLM inference engine for high-throughput workloads

willccbb:

ShishirPatil:

chiphuyen:

Created 7 months ago

Updated 1 month ago

dynamo by ai-dynamo

Inference framework for distributed generative AI model serving

vincentweisser:

willingc:

chiphuyen:

luiscape:

Created 10 months ago

Updated 16 hours ago

3FS by deepseek-ai

Distributed file system for AI training/inference workloads

chiphuyen:

joewalnes:

wesm:

alexey-milovidov:

Created 10 months ago

Updated 5 days ago

flash-linear-attention by fla-org

Efficient Torch/Triton implementations for linear attention models

hiyouga:

zhyncs:

yang-song:

winglian:

Created 2 years ago

Updated 1 day ago

Sana by NVlabs

Image synthesis research paper using a linear diffusion transformer

chiphuyen:

sxyu:

Created 1 year ago

Updated 3 weeks ago

Trace by microsoft

AutoDiff-like tool for end-to-end AI agent training with general feedback

ekzhu:

transitive-bullshit:

jaredpalmer:

yiranwu0:

Created 1 year ago

Updated 1 month ago

lectures by gpu-mode

Lecture series for GPU-accelerated computing

cournape:

stas00:

danielhanchen:

willccbb:

Created 2 years ago

Updated 1 month ago

swarm by openai

Multi-agent orchestration framework for lightweight agent coordination

vincentweisser:

rodrigosnader:

achowdhery:

huybery:

Created 1 year ago

Updated 10 months ago

ComfyUI by Comfy-Org

Visual AI engine for diffusion models, API, and backend

jmorganca:

jaretburkett:

dguido:

shimmyshimmer:

Created 3 years ago

Updated 17 hours ago

distrifuser by mit-han-lab

Research paper for distributed parallel inference of high-resolution diffusion models

philschmid:

merrymercy:

Created 1 year ago

Updated 1 year ago

veScale by volcengine

PyTorch-native framework for LLM training

JustinLin610:

casper-hansen:

hiyouga:

stas00:

Created 1 year ago

Updated 1 month ago

flashinfer by flashinfer-ai

Kernel library for LLM serving

chiphuyen:

hammer:

JustinLin610:

luiscape:

Created 2 years ago

Updated 15 hours ago

sglang by sgl-project

Fast serving framework for LLMs and vision language models

shimmyshimmer:

beyang:

samlambert:

ebursztein:

Created 2 years ago

Updated 14 hours ago

camel by camel-ai

Multi-agent framework for studying agent scaling laws

deshraj:

gregpr07:

didierrlopes:

hammer:

Created 2 years ago

Updated 20 hours ago

LLM-Agent-Paper-List by WooooDyy

Paper list for LLM-based agents

transitive-bullshit:

andreasjansson:

vincentweisser:

ogabrielluiz:

Created 2 years ago

Updated 4 months ago

guidance by guidance-ai

Guidance is a programming paradigm for steering LLMs

tobi:

ekzhu:

stas00:

Ying1123:

Created 3 years ago

Updated 5 days ago

scalene by plasma-umass

Python profiler with AI-powered optimization proposals

luiscape:

zhuohan123:

Ying1123:

trishume:

Created 6 years ago

Updated 2 weeks ago

generative_agents by joonspk-research

Research paper code for interactive human behavior simulation using generative agents

tobi:

sxyu:

chiphuyen:

rodrigosnader:

Created 2 years ago

Updated 1 year ago

rccl by ROCm

ROCm library for GPU collective communication routines

lysandrejik:

Created 8 years ago

Updated 22 hours ago

llama by meta-llama

Inference code for Llama 2 models (deprecated)

froystig:

fabhed:

borzunov:

calebpeffer:

Created 2 years ago

Updated 11 months ago

madrona by shacklettbp

GPU-accelerated game engine for high-throughput batch simulation

Created 3 years ago

Updated 2 months ago

mistral-inference by mistralai

Inference library for Mistral models

vincentweisser:

parano:

spartee:

transitive-bullshit:

Created 2 years ago

Updated 1 month ago

ai-town by a16z-infra

AI town starter kit for building a virtual world

tobi:

bcherny:

teknium1:

w4nderlust:

Created 2 years ago

Updated 3 days ago

milvus by milvus-io

Cloud-native vector database for scalable ANN search

luiscape:

xiaofan-luan:

jeresig:

ekzhu:

Created 6 years ago

Updated 1 day ago

dspy by stanfordnlp

Framework for programming language models, not prompting

tobi:

mateiz:

vincentweisser:

pgarbacki:

Created 3 years ago

Updated 3 days ago

dynolog by facebookincubator

Telemetry daemon for performance monitoring and tracing of heterogeneous CPU-GPU systems

Created 3 years ago

Updated 1 week ago

ChatGDB by pgosar

CLI tool for debugging with natural language via LLM

handotdev:

Ying1123:

Created 2 years ago

Updated 1 year ago

metaseq by facebookresearch

Codebase for large-scale transformer model development and deployment

chiphuyen:

gakonst:

Ying1123:

soldni:

Created 3 years ago

Updated 1 year ago

nanoGPT by karpathy

Minimalist repo for training/finetuning GPT models

tobi:

danielgross:

chiphuyen:

ankane:

Created 3 years ago

Updated 2 months ago

awesome-courses by prakhar1989

Awesome CS courses with free online materials

aravindsrinivas:

john-b-yang:

sb2nov:

infwinston:

Created 11 years ago

Updated 2 years ago

awesome-tensor-compilers by merrymercy

Curated list of tensor compiler projects and papers

chiphuyen:

infwinston:

Ying1123:

luiscape:

Created 5 years ago

Updated 1 year ago

iree by iree-org

MLIR-based compiler and runtime toolkit for machine learning models

ogabrielluiz:

mfuntowicz:

parano:

infwinston:

Created 6 years ago

Updated 22 hours ago

antares by microsoft

Compiler solution for PyTorch operator optimization on diverse accelerators

parasj:

comaniac:

merrymercy:

Created 5 years ago

Updated 8 months ago

oneflow by Oneflow-Inc

Deep learning framework for user-friendly, scalable, efficient model development

omarsar:

parano:

ppwwyyxx:

Created 9 years ago

Updated 1 month ago

distiller by IntelLabs

Neural network compression research toolkit

hanlint:

luiscape:

apsdehal:

s9xie:

Created 7 years ago

Updated 2 years ago

dgl by dmlc

Python package for deep learning on graphs

osanseviero:

jiamings:

parasj:

infwinston:

Created 7 years ago

Updated 5 months ago

AI-Infra-from-Zero-to-Hero by HuaizhengZhang

Curated list of machine learning systems resources

parasj:

simon-mo:

Created 7 years ago

Updated 5 months ago

cutlass by NVIDIA

CUDA C++ and Python DSLs for high-performance linear algebra

tridao:

chiphuyen:

joker-eph:

mattjj:

Created 8 years ago

Updated 2 days ago

tvm by apache

Compiler stack for deep learning systems

aravindsrinivas:

transitive-bullshit:

guberti:

wesm:

Created 9 years ago

Updated 1 day ago

Feedback? Help us improve.