Pinned Repositories
10417_hw2
15442_assignment3
AllDepOnTime
Optimized time-based thread assignment system that analyzed interactions among simulated dense or sparse social graph with OpenMP, Cilk, and MPI and compared speedup performances
Blocking_Waived_Estimation
This repo aims to solve worst case delay of relatively complicated network architecture with [1] Trajectory Approach; [2] Network Calculus; [3] Compositional Performance Analysis (CPA); and [4] Flow Aggregation and summarize both advantages and disadvantages of each approach and strives to seek out the optimal method under specific scenarios.
TidalDecode
TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
WCD_Calculation
This is used for the LORIA research internship and worst-case delay (WCD) calculation.
Xcircuit-GPT-Circuit-Classifier
FlexFlow
FlexFlow Serve: Low-Latency, High-Performance LLM Serving
ralm-sys
TinyChatEngine
TinyChatEngine: On-Device LLM Inference Library
DerrickYLJ's Repositories
DerrickYLJ/TidalDecode
TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
DerrickYLJ/Blocking_Waived_Estimation
This repo aims to solve worst case delay of relatively complicated network architecture with [1] Trajectory Approach; [2] Network Calculus; [3] Compositional Performance Analysis (CPA); and [4] Flow Aggregation and summarize both advantages and disadvantages of each approach and strives to seek out the optimal method under specific scenarios.
DerrickYLJ/WCD_Calculation
This is used for the LORIA research internship and worst-case delay (WCD) calculation.
DerrickYLJ/Xcircuit-GPT-Circuit-Classifier
DerrickYLJ/10417_hw2
DerrickYLJ/15442_assignment3
DerrickYLJ/AllDepOnTime
Optimized time-based thread assignment system that analyzed interactions among simulated dense or sparse social graph with OpenMP, Cilk, and MPI and compared speedup performances
DerrickYLJ/DerrickYLJ
Config files for my GitHub profile.
DerrickYLJ/FlexFlow
A distributed deep learning framework that supports flexible parallelization strategies.
DerrickYLJ/Functional-Programming-SML
Notes and assignments from the functional programming course 15-150 and give
DerrickYLJ/homework1
DerrickYLJ/lit_review_sparse
For long-context LLM and sparse attention in CMU 11-711: Advanced NLP
DerrickYLJ/minllama-assignment
For advanced nlp course
DerrickYLJ/publish-to-gcr
Docker Image Publish Testing
DerrickYLJ/workflow_test
testing self-hosted machine for FlexFlow