flexflow / flexflow-trainLinks
Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training
☆1,803Updated this week
Alternatives and similar repositories for flexflow-train
Users that are interested in flexflow-train are comparing it to the libraries listed below
Sorting:
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,020Updated 2 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,426Updated 11 months ago
- Serving multiple LoRA finetuned LLM as one☆1,066Updated last year
- FlashInfer: Kernel Library for LLM Serving☆3,211Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,491Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,258Updated 3 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,081Updated last week
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,088Updated 2 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆845Updated 9 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,128Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆825Updated 2 weeks ago
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,835Updated last year
- Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackab…☆1,571Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,325Updated last week
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,549Updated 11 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆705Updated 3 months ago
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,317Updated this week
- Microsoft Automatic Mixed Precision Library☆609Updated 8 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,395Updated last year
- ☆593Updated last month
- Pipeline Parallelism for PyTorch☆768Updated 10 months ago
- A PyTorch Native LLM Training Framework☆819Updated 5 months ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆429Updated 2 months ago
- Transformer related optimization, including BERT, GPT☆6,211Updated last year
- Disaggregated serving system for Large Language Models (LLMs).☆617Updated 2 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,193Updated last month
- Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA☆868Updated this week
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,055Updated this week
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆474Updated last year
- Tutel MoE: Optimized Mixture-of-Experts Library, Support DeepSeek FP8/FP4☆842Updated this week