alipay / PainlessInferenceAccelerationLinks
Accelerate inference without tears
☆370Updated 3 weeks ago
Alternatives and similar repositories for PainlessInferenceAcceleration
Users that are interested in PainlessInferenceAcceleration are comparing it to the libraries listed below
Sorting:
- A flexible and efficient training framework for large-scale alignment tasks☆442Updated last month
- Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).☆250Updated last year
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆270Updated 4 months ago
- Best practice for training LLaMA models in Megatron-LM☆663Updated last year
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆415Updated 3 months ago
- LLM Inference benchmark☆431Updated last year
- ☆515Updated 3 weeks ago
- Efficient AI Inference & Serving☆478Updated last year
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆70Updated 2 years ago
- Collaborative Training of Large Language Models in an Efficient Way☆417Updated last year
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆940Updated this week
- [ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.☆253Updated last year
- ☆179Updated last week
- FlagScale is a large model toolkit based on open-sourced projects.☆421Updated last week
- Efficient Training (including pre-training and fine-tuning) for Big Models☆613Updated last month
- A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarks☆269Updated last year
- An Efficient "Factory" to Build Multiple LoRA Adapters☆358Updated 9 months ago
- ☆115Updated last year
- Mixture-of-Experts (MoE) Language Model☆192Updated last year
- ☆79Updated last year
- Fast inference from large lauguage models via speculative decoding☆860Updated last year
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆98Updated last year
- LongBench v2 and LongBench (ACL 25'&24')☆1,032Updated 10 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆488Updated last year
- ☆153Updated 9 months ago
- A high-performance inference system for large language models, designed for production environments.☆487Updated last month
- 青稞Talk☆173Updated last week
- The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…☆394Updated last year
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆225Updated 2 years ago
- LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training☆406Updated 4 months ago