IST-DASLab / Sparse-MarlinLinks
Boosting 4-bit inference kernels with 2:4 Sparsity
☆90Updated 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:
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆136Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆175Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆139Updated 7 months ago
- ☆157Updated 10 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆118Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆259Updated 3 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆332Updated last year
- ☆115Updated last year
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆155Updated 2 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆276Updated 5 months ago
- ☆85Updated 11 months ago
- ☆100Updated last year
- extensible collectives library in triton☆91Updated 9 months ago
- KV cache compression for high-throughput LLM inference☆148Updated 11 months ago
- ☆133Updated 7 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆92Updated 3 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆220Updated last year
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆123Updated last year
- ☆116Updated 7 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆153Updated 4 months ago
- A bunch of kernels that might make stuff slower 😉☆73Updated last week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆397Updated last year
- Code for data-aware compression of DeepSeek models☆66Updated last month
- Fast low-bit matmul kernels in Triton☆418Updated 3 weeks 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☆228Updated this week
- Fast Hadamard transform in CUDA, with a PyTorch interface☆271Updated 2 months ago
- Autonomous GPU Kernel Generation via Deep Agents☆202Updated this week
- Ship correct and fast LLM kernels to PyTorch☆130Updated this week