AutonomicPerfectionist / PipeInfer
PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation
☆29Updated 5 months ago
Alternatives and similar repositories for PipeInfer:
Users that are interested in PipeInfer are comparing it to the libraries listed below
- ☆45Updated 9 months ago
- ☆59Updated 10 months ago
- LLM Serving Performance Evaluation Harness☆77Updated 2 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆36Updated 3 weeks ago
- Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"☆29Updated last year
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆34Updated last week
- ☆68Updated 3 months ago
- ☆53Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆115Updated 4 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆35Updated last week
- LLM Inference analyzer for different hardware platforms☆62Updated 2 weeks ago
- ☆31Updated last week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆159Updated 9 months ago
- ☆52Updated last month
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆154Updated 7 months ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆106Updated 6 months ago
- ☆140Updated 9 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆46Updated 5 months ago
- 16-fold memory access reduction with nearly no loss☆90Updated last month
- Stateful LLM Serving☆63Updated last month
- Explore Inter-layer Expert Affinity in MoE Model Inference☆8Updated 11 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆208Updated 5 months ago
- ☆30Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆72Updated 7 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆51Updated 10 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆85Updated last year
- Modular and structured prompt caching for low-latency LLM inference☆91Updated 5 months ago
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆109Updated 11 months ago
- ☆69Updated last week
- A minimal implementation of vllm.☆39Updated 8 months ago