Raincleared-Song / sparse_gpu_operator
GPU operators for sparse tensor operations
☆31Updated last year
Alternatives and similar repositories for sparse_gpu_operator:
Users that are interested in sparse_gpu_operator are comparing it to the libraries listed below
- Odysseus: Playground of LLM Sequence Parallelism☆66Updated 9 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆71Updated 6 months ago
- ☆24Updated 4 months ago
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆47Updated 11 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆51Updated 9 months ago
- 16-fold memory access reduction with nearly no loss☆81Updated last week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆157Updated 8 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆62Updated this week
- ☆22Updated last year
- ☆118Updated last month
- Repository for CPU Kernel Generation for LLM Inference☆25Updated last year
- ☆65Updated 2 months ago
- ☆52Updated 11 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆56Updated last year
- Multi-Candidate Speculative Decoding☆35Updated 11 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆299Updated 8 months ago
- ☆51Updated 2 weeks ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆89Updated last month
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆87Updated this week
- ☆28Updated 11 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆74Updated 4 months ago
- ☆64Updated 3 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆59Updated 5 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆104Updated this week
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆24Updated last year
- [ICLR 2025] PEARL: parallel speculative decoding with adaptive draft length☆59Updated last week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆110Updated 3 months ago
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆47Updated 8 months ago
- Quantized Attention on GPU☆45Updated 4 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆30Updated 3 weeks ago