- Homepage: weilin-zhao.com
- 🌱 I'm a PhD student at Tsinghua University, THUNLP lab.
- 🔭 I’m currently working on Efficient LLM.
- ⚡ I’m one of the maintainers of the following open-source projects: CPM.cu, BMTrain, OpenPrompt and OpenDelta.
Pinned Loading
-
thunlp/FR-Spec
thunlp/FR-Spec Public[ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
-
OpenBMB/CPM.cu
OpenBMB/CPM.cu PublicCPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge techniques in sparse architecture, speculative sampling and qua…
-
OpenBMB/BMTrain
OpenBMB/BMTrain PublicEfficient Training (including pre-training and fine-tuning) for Big Models
-
thunlp/Ouroboros
thunlp/Ouroboros PublicOuroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
-
thunlp/OpenPrompt
thunlp/OpenPrompt PublicAn Open-Source Framework for Prompt-Learning.
-
OpenBMB/MiniCPM
OpenBMB/MiniCPM PublicMiniCPM4: Ultra-Efficient LLMs on End Devices, achieving 5+ speedup on typical end-side chips
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.