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 5 months ago
- ☆68Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆176Updated 11 months ago
- Stateful LLM Serving☆81Updated 5 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆124Updated 8 months ago
- ☆120Updated 10 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆128Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆57Updated 9 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆90Updated 2 years ago
- Modular and structured prompt caching for low-latency LLM inference☆98Updated 9 months ago
- Compression for Foundation Models☆35Updated last month
- A resilient distributed training framework☆94Updated last year
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆226Updated 9 months ago
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆61Updated this week
- A framework for generating realistic LLM serving workloads☆53Updated 2 months ago
- ☆16Updated 2 months ago
- KV cache compression for high-throughput LLM inference☆134Updated 6 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆52Updated 3 weeks ago
- ☆113Updated 9 months ago
- ☆78Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation☆30Updated 9 months ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆23Updated last year
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆66Updated 2 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆221Updated last month
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆47Updated last year
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆217Updated last year
- Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"☆34Updated last month
- A low-latency & high-throughput serving engine for LLMs☆405Updated 2 months ago
- ☆279Updated last week