tyler-griggs / melange-releaseLinks
☆47Updated last year
Alternatives and similar repositories for melange-release
Users that are interested in melange-release are comparing it to the libraries listed below
Sorting:
- LLM Serving Performance Evaluation Harness☆79Updated 8 months ago
- ☆74Updated last week
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆129Updated last year
- Stateful LLM Serving☆87Updated 7 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆186Updated last year
- ☆136Updated last year
- Compression for Foundation Models☆35Updated 3 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆130Updated 10 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆60Updated 11 months ago
- Modular and structured prompt caching for low-latency LLM inference☆100Updated 11 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆92Updated 2 years ago
- A resilient distributed training framework☆95Updated last year
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation☆30Updated 11 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆238Updated 11 months ago
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆59Updated 3 weeks ago
- ☆78Updated 6 months ago
- KV cache compression for high-throughput LLM inference☆142Updated 8 months ago
- ☆124Updated 11 months ago
- ☆18Updated 4 months ago
- ☆63Updated last month
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆63Updated last month
- ☆43Updated 5 months ago
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆88Updated last month
- A framework for generating realistic LLM serving workloads☆71Updated 2 weeks ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆75Updated 4 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆252Updated last week
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆104Updated this week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆169Updated last year
- Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and …☆34Updated last month
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆39Updated 7 months ago