tspeterkim / paged-attention-minimalLinks
a minimal cache manager for PagedAttention, on top of llama3.
☆124Updated 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☆381Updated 3 weeks ago
- Cataloging released Triton kernels.☆263Updated last month
- Applied AI experiments and examples for PyTorch☆299Updated 2 months ago
- ☆240Updated this week
- Collection of kernels written in Triton language☆157Updated 6 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆264Updated this week
- ring-attention experiments☆154Updated last year
- A minimal implementation of vllm.☆58Updated last year
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆233Updated 5 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆124Updated 4 months ago
- ☆240Updated last year
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆215Updated last week
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆221Updated 2 years ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- ☆92Updated 11 months ago
- extensible collectives library in triton☆89Updated 6 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆118Updated last year
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆237Updated 11 months ago
- Fastest kernels written from scratch☆374Updated last month
- A bunch of kernels that might make stuff slower 😉☆62Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 3 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆83Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆246Updated 3 weeks ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆116Updated last year
- Utility scripts for PyTorch (e.g. Memory profiler that understands more low-level allocations such as NCCL)☆59Updated last month
- A collection of memory efficient attention operators implemented in the Triton language.☆282Updated last year
- ☆112Updated last year
- ☆82Updated 9 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆389Updated last year
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆119Updated 3 weeks ago