Thunderbeee/ZSCL
Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models
Repositories
Thunderbeee/bench_serving
Thunderbeee/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Thunderbeee/nv-srt-slurm
NVIDIA Inference Benchmarks provide recipes in ready-to-use templates for evaluating platform speed. Validate your platform across specific AI use cases across hardware and software combinations.
Thunderbeee/multi-llm-serving
Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.
Thunderbeee/srt-slurm
Benchmark SGLang on SLURM
Thunderbeee/Thunderbeee.github.io
Thunderbeee/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.
Thunderbeee/kvcached
kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.
Thunderbeee/Image_Recognition_Project
Thunderbeee/Awesome-ML-SYS-Tutorial
My learning notes/codes for ML SYS.
Thunderbeee/cs184_rlhf
Thunderbeee/Thunderbeee
Thunderbeee/data-versioning
Thunderbeee/MIT_6.s986
Thunderbeee/CS209B
Thunderbeee/cs265-mlsys
Thunderbeee/mlsys
Thunderbeee/Math_LLM
Code for MIT 6.S986 project
Thunderbeee/CUDA_by_practice
CUDA by practice
Thunderbeee/yelp_ac209a
Thunderbeee/msra_rap
Thunderbeee/RAP
Reasoning with Language Model is Planning with World Model
Thunderbeee/LLM-Adapters
LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models
Thunderbeee/RWKV-LM
Thunderbeee/MEGABYTE-pytorch
Thunderbeee/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Thunderbeee/alpaca
Thunderbeee/NLP-attitude-score
Thunderbeee/hai-cooking
Human-AI-Collaboration (cooking setting)