tspeterkim / paged-attention-minimalLinks
a minimal cache manager for PagedAttention, on top of llama3.
☆120Updated last year
Alternatives and similar repositories for paged-attention-minimal
Users that are interested in paged-attention-minimal are comparing it to the libraries listed below
Sorting:
- Fast low-bit matmul kernels in Triton☆357Updated this week
- Cataloging released Triton kernels.☆252Updated this week
- Applied AI experiments and examples for PyTorch☆295Updated 3 weeks ago
- ☆233Updated 3 weeks ago
- Collection of kernels written in Triton language☆154Updated 5 months ago
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆219Updated 4 months ago
- A minimal implementation of vllm.☆52Updated last year
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆230Updated 9 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆221Updated this week
- ring-attention experiments☆150Updated 10 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆319Updated last year
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆209Updated last week
- ☆230Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆113Updated 3 months ago
- extensible collectives library in triton☆88Updated 5 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆118Updated last year
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆219Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆263Updated last month
- Boosting 4-bit inference kernels with 2:4 Sparsity☆82Updated last year
- ☆88Updated 10 months ago
- A Quirky Assortment of CuTe Kernels☆450Updated last week
- kernels, of the mega variety☆486Updated 3 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆114Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆414Updated 3 months ago
- Fastest kernels written from scratch☆323Updated 5 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆319Updated 7 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆377Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆238Updated 2 weeks ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆747Updated 6 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆277Updated last year