Pinned Repositories
ABR-gym
MAPPO
mini-s
pensieve
Pensieve-PPO
The simplest implementation of Pensieve (SIGCOMM' 17) via state-of-the-art RL algorithms, including PPO, DQN, and SAC
QR-DNN
This repository represents the quantization and reconstruction algorithm (QR-DNN) for the FPL 2018 paper "RNA: An Accurate Residual Network Accelerator for Quantized and Reconstructed Deep Neural Networks"
recurrent_maskable
rtp
RTP: Rethinking Tensor Parallelism with Memory Deduplication
starlink-trace-tracker
unsloth
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
wdlctc's Repositories
wdlctc/mini-s
wdlctc/starlink-trace-tracker
wdlctc/recurrent_maskable
wdlctc/rtp
RTP: Rethinking Tensor Parallelism with Memory Deduplication
wdlctc/Pensieve-PPO
The simplest implementation of Pensieve (SIGCOMM' 17) via state-of-the-art RL algorithms, including PPO, DQN, and SAC
wdlctc/unsloth
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
wdlctc/coconet
wdlctc/colab
wdlctc/efficient_cross_entropy
wdlctc/FlexFlow
FlexFlow Serve: Low-Latency, High-Performance LLM Serving
wdlctc/LASP
Linear Attention Sequence Parallelism (LASP)
wdlctc/LongLoRA
Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
wdlctc/nccl_test
wdlctc/neuraloperator
Learning in infinite dimension with neural operators.
wdlctc/Open-Sora-old
Building your own video generation model like OpenAI's Sora
wdlctc/OpenDiT
OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference
wdlctc/peft_minis
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
wdlctc/PyTAG
wdlctc/regicide
wdlctc/sevenvice
wdlctc/SIMPLE
Selfplay In MultiPlayer Environments
wdlctc/Speculative-Sampling
Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind
wdlctc/streaming-llm
Efficient Streaming Language Models with Attention Sinks
wdlctc/tensorly
TensorLy: Tensor Learning in Python.
wdlctc/tltorch
TensorLy-Torch: Deep Tensor Learning with TensorLy and PyTorch
wdlctc/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
wdlctc/triton
Development repository for the Triton language and compiler
wdlctc/VisionLLaMA
wdlctc/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
wdlctc/wdlctc.github.io