cli99 / llm-analysisLinks
Latency and Memory Analysis of Transformer Models for Training and Inference
☆475Updated 8 months ago
Alternatives and similar repositories for llm-analysis
Users that are interested in llm-analysis are comparing it to the libraries listed below
Sorting:
- A low-latency & high-throughput serving engine for LLMs☆462Updated 2 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆454Updated 7 months ago
- Zero Bubble Pipeline Parallelism☆444Updated 8 months ago
- ☆351Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆332Updated last year
- A large-scale simulation framework for LLM inference☆509Updated 5 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆231Updated 2 years ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆602Updated last year
- Disaggregated serving system for Large Language Models (LLMs).☆758Updated 9 months ago
- ☆614Updated 7 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆799Updated 10 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆220Updated last year
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆498Updated last year
- A curated list of awesome projects and papers for distributed training or inference☆262Updated last year
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆282Updated 10 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆269Updated 2 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆287Updated last year
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆597Updated last week
- nnScaler: Compiling DNN models for Parallel Training☆122Updated 3 months ago
- Allow torch tensor memory to be released and resumed later☆196Updated last month
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆396Updated last year
- ☆122Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆929Updated 2 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆276Updated 5 months ago
- A minimal implementation of vllm.☆64Updated last year
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆93Updated 2 years ago
- ☆89Updated 3 years ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆978Updated last year
- ☆153Updated 10 months ago
- Applied AI experiments and examples for PyTorch☆312Updated 4 months ago