ChengZhang-98 / llm-mixed-qLinks
Official implementation of EMNLP'23 paper "Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?"
☆22Updated last year
Alternatives and similar repositories for llm-mixed-q
Users that are interested in llm-mixed-q are comparing it to the libraries listed below
Sorting:
- ☆41Updated 5 months ago
- ☆98Updated last year
- Implementation of Microscaling data formats in SystemVerilog.☆19Updated 9 months ago
- ☆27Updated this week
- Simulator for BitFusion☆100Updated 4 years ago
- ☆41Updated 11 months ago
- MICRO22 artifact evaluation for Sparseloop☆43Updated 2 years ago
- ☆34Updated 4 years ago
- A co-design architecture on sparse attention☆52Updated 3 years ago
- [TCAD'23] AccelTran: A Sparsity-Aware Accelerator for Transformers☆43Updated last year
- An efficient spatial accelerator enabling hybrid sparse attention mechanisms for long sequences☆27Updated last year
- Tender: Accelerating Large Language Models via Tensor Decompostion and Runtime Requantization (ISCA'24)☆14Updated 11 months ago
- Serpens is an HBM FPGA accelerator for SpMV☆19Updated 10 months ago
- [ASPLOS 2024] CIM-MLC: A Multi-level Compilation Stack for Computing-In-Memory Accelerators☆36Updated last year
- ☆27Updated 2 months ago
- A framework for fast exploration of the depth-first scheduling space for DNN accelerators☆39Updated 2 years ago
- [HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning☆93Updated 9 months ago
- RTL implementation of Flex-DPE.☆100Updated 5 years ago
- Multi-core HW accelerator mapping optimization framework for layer-fused ML workloads.☆53Updated last month
- HW accelerator mapping optimization framework for in-memory computing☆24Updated this week
- ☆33Updated 3 years ago
- An open-source parameterizable NPU generator with full-stack multi-target compilation stack for intelligent workloads.☆53Updated 2 months ago
- The codes and artifacts associated with our MICRO'22 paper titled: "Adaptable Butterfly Accelerator for Attention-based NNs via Hardware …☆135Updated 2 years ago
- ☆45Updated 3 years ago
- Model LLM inference on single-core dataflow accelerators☆10Updated 3 months ago
- ☆16Updated 2 years ago
- ☆18Updated 2 years ago
- A scheduler for spatial DNN accelerators that generate high-performance schedules in one shot using mixed integer programming (MIP)☆79Updated last year
- ☆71Updated 2 years ago
- Codebase for the Progressive Mixed-Precision Decoding paper.☆11Updated 4 months ago