IST-DASLab / MoE-QuantLinks
Code for data-aware compression of DeepSeek models
☆36Updated last month
Alternatives and similar repositories for MoE-Quant
Users that are interested in MoE-Quant are comparing it to the libraries listed below
Sorting:
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 10 months ago
- ☆136Updated 5 months ago
- ☆71Updated 2 weeks ago
- KV cache compression for high-throughput LLM inference☆132Updated 5 months ago
- ☆139Updated 3 weeks ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆121Updated 7 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆118Updated last month
- 16-fold memory access reduction with nearly no loss☆100Updated 3 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆125Updated 4 months ago
- ☆116Updated last month
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆117Updated last year
- A safetensors extension to efficiently store sparse quantized tensors on disk☆135Updated this week
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆311Updated 5 months ago
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆139Updated this week
- Work in progress.☆70Updated 2 weeks ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆218Updated 7 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆138Updated last month
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆360Updated 11 months ago
- ☆173Updated this week
- Fast low-bit matmul kernels in Triton☆330Updated this week
- The evaluation framework for training-free sparse attention in LLMs☆82Updated 3 weeks ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆138Updated 11 months ago
- extensible collectives library in triton☆87Updated 3 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆142Updated last month
- [ICML 2025] SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆34Updated 11 months ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆109Updated 9 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆224Updated 7 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆313Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆101Updated last month