IST-DASLab / SparseFinetuningLinks
Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry
☆42Updated last year
Alternatives and similar repositories for SparseFinetuning
Users that are interested in SparseFinetuning are comparing it to the libraries listed below
Sorting:
- Boosting 4-bit inference kernels with 2:4 Sparsity☆75Updated 8 months ago
- Repository for CPU Kernel Generation for LLM Inference☆26Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 7 months ago
- QuIP quantization☆52Updated last year
- Work in progress.☆67Updated this week
- ☆129Updated 3 months ago
- Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"☆17Updated 2 weeks ago
- Official implementation of "The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs"☆32Updated last month
- Official implementation of the ICML 2024 paper RoSA (Robust Adaptation)☆42Updated last year
- ☆28Updated 10 months ago
- ☆125Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆163Updated 10 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆69Updated 11 months ago
- Vocabulary Parallelism☆19Updated 2 months ago
- ☆45Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆116Updated 6 months ago
- PB-LLM: Partially Binarized Large Language Models☆152Updated last year
- ☆24Updated 6 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆62Updated 4 months ago
- ☆30Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆46Updated 7 months ago
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆26Updated last month
- ☆38Updated 6 months ago
- Cascade Speculative Drafting☆29Updated last year
- ☆45Updated 3 months ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆107Updated 7 months ago
- Using FlexAttention to compute attention with different masking patterns☆43Updated 8 months ago
- ☆73Updated 4 months ago
- ☆50Updated 7 months ago
- Low-Rank Llama Custom Training☆22Updated last year