OpenBMB / infllmv2_cuda_implLinks
☆55Updated last week
Alternatives and similar repositories for infllmv2_cuda_impl
Users that are interested in infllmv2_cuda_impl are comparing it to the libraries listed below
Sorting:
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆143Updated 4 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆241Updated last month
- ☆129Updated 4 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆155Updated last week
- Odysseus: Playground of LLM Sequence Parallelism☆77Updated last year
- qwen-nsa☆75Updated 5 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆43Updated 3 months ago
- ☆98Updated 4 months ago
- Efficient triton implementation of Native Sparse Attention.☆226Updated 4 months ago
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- ☆50Updated 4 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆249Updated last week
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆187Updated last month
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆234Updated 3 months ago
- ☆119Updated 4 months ago
- A sparse attention kernel supporting mix sparse patterns☆311Updated 7 months ago
- ☆112Updated last month
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆146Updated 2 months ago
- ☆95Updated 6 months ago
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆68Updated last month
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆110Updated 6 months ago
- ☆142Updated 7 months ago
- ☆147Updated 7 months ago
- Estimate MFU for DeepSeekV3☆24Updated 9 months ago
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆40Updated 3 weeks ago
- ☆64Updated 5 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆141Updated last month
- PyTorch bindings for CUTLASS grouped GEMM.☆123Updated 4 months ago
- Quantized Attention on GPU☆44Updated 10 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆117Updated 5 months ago