tyler-griggs / melange-release
☆35Updated 2 months ago
Related projects: ⓘ
- ☆32Updated this week
- LLM Serving Performance Evaluation Harness☆45Updated 3 weeks ago
- A resilient distributed training framework☆78Updated 5 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆92Updated 6 months ago
- Stateful LLM Serving☆25Updated last month
- ☆30Updated 3 months ago
- ☆47Updated 3 weeks ago
- Modular and structured prompt caching for low-latency LLM inference☆43Updated 4 months ago
- ☆30Updated this week
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆70Updated last year
- Fast Inference of MoE Models with CPU-GPU Orchestration☆163Updated 3 months ago
- A low-latency & high-throughput serving engine for LLMs☆174Updated last week
- Efficient serverless deployment for large AI models.☆178Updated this week
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆55Updated this week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆89Updated last week
- A minimal implementation of vllm.☆29Updated last month
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆90Updated last month
- Bamboo-7B Large Language Model☆88Updated 5 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆134Updated 2 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆110Updated last month
- A large-scale simulation framework for LLM inference☆236Updated 3 weeks ago
- ☆19Updated last year
- ☆29Updated 3 weeks ago
- Official Repo for "LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization"☆25Updated 6 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆29Updated 6 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆84Updated 2 months ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆13Updated 9 months ago
- ☆15Updated 2 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆47Updated 2 weeks ago
- ☆90Updated 2 years ago