cli99 / llm-analysis
Latency and Memory Analysis of Transformer Models for Training and Inference
☆355Updated last week
Related projects ⓘ
Alternatives and complementary repositories for llm-analysis
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆195Updated 3 months ago
- Zero Bubble Pipeline Parallelism☆282Updated last week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆278Updated 4 months ago
- A low-latency & high-throughput serving engine for LLMs☆247Updated 2 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆240Updated last week
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆312Updated 2 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆393Updated 3 months ago
- A large-scale simulation framework for LLM inference☆278Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆362Updated 3 months ago
- ☆289Updated 7 months ago
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆446Updated 2 weeks ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆627Updated 2 months ago
- ☆111Updated 8 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆305Updated 3 months ago
- A curated list of awesome projects and papers for distributed training or inference☆197Updated last month
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆181Updated last year
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆362Updated this week
- A fast communication-overlapping library for tensor parallelism on GPUs.☆225Updated 3 weeks ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆203Updated 3 weeks ago
- A baseline repository of Auto-Parallelism in Training Neural Networks☆141Updated 2 years ago
- Explorations into some recent techniques surrounding speculative decoding☆212Updated last year
- Applied AI experiments and examples for PyTorch☆168Updated 3 weeks ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆209Updated 3 weeks ago
- A collection of memory efficient attention operators implemented in the Triton language.☆219Updated 5 months ago
- Efficient and easy multi-instance LLM serving☆216Updated this week
- This repository contains integer operators on GPUs for PyTorch.☆183Updated last year
- ☆169Updated 4 months ago
- Materials for learning SGLang☆105Updated this week
- Making Long-Context LLM Inference 10x Faster and 10x Cheaper☆236Updated this week
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆190Updated 3 weeks ago