eth-easl / deltazip
Compression for Foundation Models
☆30Updated last week
Alternatives and similar repositories for deltazip:
Users that are interested in deltazip are comparing it to the libraries listed below
- ☆45Updated 9 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆40Updated last year
- Beyond KV Caching: Shared Attention for Efficient LLMs☆17Updated 8 months ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆105Updated 5 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆39Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆72Updated 6 months ago
- ☆13Updated last week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆111Updated 4 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆31Updated this week
- LLM Serving Performance Evaluation Harness☆73Updated last month
- A minimal implementation of vllm.☆37Updated 8 months ago
- ☆24Updated 4 months ago
- 16-fold memory access reduction with nearly no loss☆86Updated last week
- FlexAttention w/ FlashAttention3 Support☆26Updated 5 months ago
- ☆68Updated 2 months ago
- ☆49Updated 2 weeks ago
- Cascade Speculative Drafting☆29Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆158Updated 8 months ago
- ☆11Updated 7 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆68Updated 9 months ago
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation☆28Updated 4 months ago
- ☆36Updated 4 months ago
- ☆52Updated last week
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆85Updated last year
- FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation☆47Updated 8 months ago
- ☆37Updated 5 months ago
- Quantized Attention on GPU☆45Updated 4 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆51Updated 9 months ago
- ☆20Updated last year
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆202Updated 4 months ago