liz-badada/aisimulate
AISimulate predicts LLM serving behavior and searches for strong deployment configurations offline, without bringing up a GPU serving cluster
Hahahahahahahaha
Repositories
liz-badada/sglang
SGLang is a fast serving framework for large language models and vision language models.
liz-badada/verl-recipe
A set of examples based on verl for end-to-end RL training recipes.
liz-badada/DeepGEMM-SA
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
liz-badada/flashinfer
FlashInfer: Kernel Library for LLM Serving
liz-badada/dynamo
A Datacenter Scale Distributed Inference Serving Framework
liz-badada/vllm-omni
A framework for efficient model inference with omni-modality models
liz-badada/beat-ai
<Beat AI> 又名 <零生万物> , 是一本专属于软件开发工程师的 AI 入门圣经，手把手带你上手写 AI。从神经网络到大模型，从高层设计到微观原理，从工程实现到算法，学完后，你会发现 AI 也并不是想象中那么高不可攀、无法战胜，Just beat it !
liz-badada/FastAFD
liz-badada/DeepGEMM
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
liz-badada/aiconfigurator
Offline optimization of your disaggregated Dynamo graph
liz-badada/verl
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
liz-badada/ptx-isa-markdown
PTX ISA 9.1 documentation converted to searchable markdown. Includes Claude Code skill for CUDA development.
liz-badada/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
liz-badada/liz-badada.github.io
liz-badada/autoresearch
AI agents running research on single-GPU nanochat training automatically
liz-badada/srt-slurm
Benchmark SGLang on SLURM
liz-badada/cutile-python
cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
liz-badada/TileGym
Helpful kernel tutorials and examples for tile-based GPU programming
liz-badada/cutlass
CUDA Templates and Python DSLs for High-Performance Linear Algebra
liz-badada/AISystem
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
liz-badada/gpu-datasheet
liz-badada/quack
A Quirky Assortment of CuTe Kernels
liz-badada/simple-evals
liz-badada/TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in performant way.
liz-badada/lm-sys.github.io
liz-badada/Mooncake
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
liz-badada/3FS
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
liz-badada/DeepEP
DeepEP: an efficient expert-parallel communication library
liz-badada/profile-data
Analyze computation-communication overlap in V3/R1.