zhengzangw / Sequence-SchedulingLinks
PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
☆90Updated 2 years ago
Alternatives and similar repositories for Sequence-Scheduling
Users that are interested in Sequence-Scheduling are comparing it to the libraries listed below
Sorting:
- ☆85Updated 3 years ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆57Updated 9 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆176Updated 11 months ago
- ☆56Updated 8 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆217Updated last year
- A resilient distributed training framework☆94Updated last year
- ☆113Updated 9 months ago
- ☆54Updated last year
- ☆68Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆128Updated last year
- 16-fold memory access reduction with nearly no loss☆104Updated 4 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆106Updated 4 months ago
- ☆120Updated 10 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆321Updated last month
- ☆77Updated 10 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆48Updated last year
- ☆78Updated 4 months ago
- Stateful LLM Serving☆81Updated 5 months ago
- nnScaler: Compiling DNN models for Parallel Training☆115Updated this week
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆27Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆214Updated last year
- ☆273Updated last month
- ☆332Updated last year
- ATC23 AE☆46Updated 2 years ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆466Updated last year
- ☆131Updated last month
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆221Updated last month
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆266Updated 5 months ago