graphcore-research / llm-inference-research
An experimentation platform for LLM inference optimisation
☆29Updated 5 months ago
Alternatives and similar repositories for llm-inference-research:
Users that are interested in llm-inference-research are comparing it to the libraries listed below
- 16-fold memory access reduction with nearly no loss☆77Updated this week
- ☆52Updated 10 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆133Updated last week
- ☆221Updated 9 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆157Updated 7 months ago
- Explore Inter-layer Expert Affinity in MoE Model Inference☆7Updated 9 months ago
- Multi-Candidate Speculative Decoding☆34Updated 10 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆26Updated 2 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆199Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆246Updated 3 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆107Updated 2 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆272Updated last month
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆81Updated last year
- ☆50Updated 8 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆27Updated last week
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆96Updated 2 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆48Updated 7 months ago
- ☆76Updated 2 years ago
- ☆100Updated 5 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆160Updated last week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆295Updated 7 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆139Updated 7 months ago
- ☆78Updated last month
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆66Updated last month
- [ICLR 2025] PEARL: parallel speculative decoding with adaptive draft length☆39Updated this week
- ☆56Updated 4 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆84Updated 4 months ago
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆76Updated this week
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆306Updated 2 weeks ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆64Updated 5 months ago