tspeterkim / paged-attention-minimalLinks
a minimal cache manager for PagedAttention, on top of llama3.
☆133Updated 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:
- Cataloging released Triton kernels.☆291Updated 4 months ago
- Fast low-bit matmul kernels in Triton☆424Updated this week
- ☆277Updated this week
- Applied AI experiments and examples for PyTorch☆314Updated 5 months ago
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆249Updated 8 months ago
- Collection of kernels written in Triton language☆175Updated 9 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆319Updated this week
- ring-attention experiments☆165Updated last year
- A minimal implementation of vllm.☆66Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆335Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆141Updated 8 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆258Updated last year
- ☆258Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆93Updated last year
- ☆102Updated last year
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆219Updated this week
- ☆84Updated last year
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆119Updated last year
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆165Updated 2 months ago
- extensible collectives library in triton☆93Updated 10 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆276Updated 6 months ago
- Autonomous GPU Kernel Generation via Deep Agents☆223Updated this week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆127Updated last year
- KV cache compression for high-throughput LLM inference☆151Updated 11 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆563Updated 2 weeks ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆233Updated 2 years ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆279Updated 3 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆287Updated last year
- kernels, of the mega variety☆657Updated 4 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆457Updated 8 months ago