snowflakedb / ArcticInferenceLinks
ArcticInference: vLLM plugin for high-throughput, low-latency inference
☆288Updated this week
Alternatives and similar repositories for ArcticInference
Users that are interested in ArcticInference are comparing it to the libraries listed below
Sorting:
- ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)☆231Updated last week
- Efficient LLM Inference over Long Sequences☆390Updated 4 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆222Updated this week
- KV cache compression for high-throughput LLM inference☆143Updated 8 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆183Updated this week
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆62Updated this week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆130Updated 10 months ago
- LLM Serving Performance Evaluation Harness☆79Updated 8 months ago
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆793Updated this week
- vLLM performance dashboard☆37Updated last year
- Common recipes to run vLLM☆172Updated last week
- LLM KV cache compression made easy☆669Updated last week
- Code for data-aware compression of DeepSeek models☆56Updated 4 months ago
- Fast low-bit matmul kernels in Triton☆385Updated last week
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆469Updated this week
- Applied AI experiments and examples for PyTorch☆301Updated 2 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆238Updated 11 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆215Updated last week
- TPU inference for vLLM, with unified JAX and PyTorch support.☆123Updated this week
- Perplexity GPU Kernels☆513Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆439Updated last week
- A low-latency & high-throughput serving engine for LLMs☆431Updated 2 weeks ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆266Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆432Updated 5 months ago
- torchcomms: a modern PyTorch communications API☆103Updated last week
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆238Updated 10 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆84Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆770Updated 7 months ago
- a minimal cache manager for PagedAttention, on top of llama3.☆124Updated last year
- ☆205Updated 5 months ago