microsoft / best-route-llmLinks
Efficient LLM query routing via multi-sampling. BEST-Route selects both model and number of responses based on query difficulty, cutting costs by up to 60% with <1% performance drop. From the paper//arxiv.org/abs/2506.22716
☆33Updated 3 months ago
Alternatives and similar repositories for best-route-llm
Users that are interested in best-route-llm are comparing it to the libraries listed below
Sorting:
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- (ACL 2025 oral) SCOPE: Optimizing KV Cache Compression in Long-context Generation☆33Updated 6 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆207Updated 6 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆47Updated last year
- ☆46Updated 7 months ago
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆44Updated last month
- ☆39Updated last year
- KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference☆24Updated 6 months ago
- ☆19Updated 10 months ago
- [ICML2024 Spotlight] Fine-Tuning Pre-trained Large Language Models Sparsely☆23Updated last year
- This is the official implementation for the paper: Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models☆18Updated last year
- a curated list of high-quality papers on resource-efficient LLMs 🌱☆149Updated 8 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆36Updated 9 months ago
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆110Updated last year
- Dynamic Context Selection for Efficient Long-Context LLMs☆43Updated 6 months ago
- ☆103Updated 2 months ago
- [NAACL 2025] A Closer Look into Mixture-of-Experts in Large Language Models☆55Updated 9 months ago
- Compression for Foundation Models☆34Updated 4 months ago
- ☆20Updated 2 years ago
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆99Updated 5 months ago
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆24Updated last year
- Multi-Candidate Speculative Decoding☆37Updated last year
- [NAACL 2025 Main Selected Oral] Repository for the paper: Prompt Compression for Large Language Models: A Survey☆35Updated 6 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆82Updated 4 months ago
- ☆34Updated 9 months ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆83Updated 8 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆64Updated last year
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆48Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆80Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆50Updated last year