- 🎓 Ph.D. in Electrical Engineering from Stanford University.
- 👀 I’m interested in LLM Inference & Serving, with a focus on Quantization and Parallelism (e.g., Parallel Decoding, Speculative Decoding).
- 🌱 Currently focused on:
- CUDA Kernel Optimization
- Model Deployment & Serving Infrastructure (Paged KV Cache, Continuous Batching)
- Post-training (RLHF, Distillation, Flow-matching)
- 📫 How to reach me: linglingfan.cnn@gmail.com
- 😄 Pronouns: She/Her
{{ message }}
lfopensource
Follow
Popular repositories Loading
-
onnx-mlir
onnx-mlir PublicForked from onnx/onnx-mlir
Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure
C++ 1
-
CUDA_Kernel_Samples
CUDA_Kernel_Samples PublicForked from Tongkaio/CUDA_Kernel_Samples
CUDA 算子手撕与面试指南
Cuda 1
-
claw-code
claw-code PublicForked from ultraworkers/claw-code
Better Harness Tools, not merely storing the archive of leaked Claude Code but also make real things done. Now rewriting in Rust.
Rust 1
-
sglang
sglang PublicForked from sgl-project/sglang
SGLang is a fast serving framework for large language models and vision language models.
Python
-
TensorRT
TensorRT PublicForked from NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
C++
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.