fy1214/flashinfer
FlashInfer: Kernel Library for LLM Serving
Repositories
fy1214/ThunderKittens
Tile primitives for speedy kernels
fy1214/sglang
SGLang is a fast serving framework for large language models and vision language models.
fy1214/TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
fy1214/Megatron-LM
Ongoing research training transformer models at scale
fy1214/DeepGEMM
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
fy1214/slime
slime is a LLM post-training framework aiming for RL Scaling.
fy1214/FP4GEMM
fy1214/BasicCUDA
A tutorial for CUDA&PyTorch
fy1214/xDiT
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
fy1214/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
fy1214/cs245-as3
字节高级计划项目
fy1214/travel_web
fy1214/my_test_project
fy1214/fy1214
Config files for my GitHub profile.
fy1214/TrainingProgram
fy1214/transaction-processor
fy1214/JAVAlearning
personal java learning for 2022
fy1214/JAVA_learning
personal java learning for 2022
fy1214/JavaGuide
「Java学习+面试指南」一份涵盖大部分 Java 程序员所需要掌握的核心知识。准备 Java 面试，首选 JavaGuide！
fy1214/Java-
根据牛客网的面试宝典写的自用的java面试宝典，附带个人理解和个人阅读源码后的答案