qhliu26 / Dive-into-Big-Model-Training
Dive into Big Model Training
☆109Updated last year
Related projects: ⓘ
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆183Updated last month
- PyTorch bindings for CUTLASS grouped GEMM.☆57Updated 2 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆205Updated 3 months ago
- Zero Bubble Pipeline Parallelism☆254Updated 2 weeks ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆309Updated this week
- ☆65Updated 2 years ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆338Updated 3 months ago
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆156Updated 3 months ago
- ☆108Updated 6 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆127Updated 3 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆161Updated 2 months ago
- ATC23 AE☆42Updated last year
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆41Updated last month
- ☆60Updated last month
- [NeurIPS 2022] A Fast Post-Training Pruning Framework for Transformers☆160Updated last year
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆240Updated 2 weeks ago
- Explorations into some recent techniques surrounding speculative decoding☆190Updated 11 months ago
- Low-bit optimizers for PyTorch☆109Updated 11 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆166Updated last month
- ☆83Updated 3 weeks ago
- ☆164Updated 4 months ago
- A Python library transfers PyTorch tensors between CPU and NVMe☆92Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆186Updated last month
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆70Updated last year
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆158Updated 4 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆166Updated 11 months ago
- Ring attention implementation with flash attention☆529Updated this week
- ☆269Updated 5 months ago
- A high-performance distributed deep learning system targeting large-scale and automated distributed training. If you have any interests, …☆101Updated 9 months ago
- This repository contains integer operators on GPUs for PyTorch.☆172Updated 11 months ago