IST-DASLab / Sparse-MarlinLinks
Boosting 4-bit inference kernels with 2:4 Sparsity
☆82Updated last year
Alternatives and similar repositories for Sparse-Marlin
Users that are interested in Sparse-Marlin are comparing it to the libraries listed below
Sorting:
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆128Updated 9 months ago
- ☆142Updated 7 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆241Updated last month
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆121Updated 4 months ago
- ☆112Updated last year
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆118Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 2 months ago
- KV cache compression for high-throughput LLM inference☆141Updated 7 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆146Updated last year
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- extensible collectives library in triton☆88Updated 6 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆216Updated last year
- ☆82Updated 8 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆383Updated last year
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆234Updated 10 months ago
- ☆126Updated 4 months ago
- ☆90Updated 10 months ago
- ☆74Updated 6 months ago
- Code for data-aware compression of DeepSeek models☆54Updated 3 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- A safetensors extension to efficiently store sparse quantized tensors on disk☆164Updated this week
- Odysseus: Playground of LLM Sequence Parallelism☆77Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆140Updated last month
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆110Updated 6 months ago
- ☆280Updated 2 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆115Updated last year
- Applied AI experiments and examples for PyTorch☆296Updated last month
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆99Updated 3 weeks ago