mit-han-lab / fouroversixLinks
Code for the paper “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling”
☆93Updated this week
Alternatives and similar repositories for fouroversix
Users that are interested in fouroversix are comparing it to the libraries listed below
Sorting:
- ☆83Updated 11 months ago
- ☆60Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆159Updated 2 months ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆148Updated last month
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆169Updated last month
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆202Updated last month
- LLM Inference with Microscaling Format☆34Updated last year
- [ICML 2025] SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆46Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆135Updated 6 months ago
- Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)☆79Updated 5 months ago
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆122Updated 5 months ago
- ☆89Updated last month
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆261Updated 5 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆267Updated 2 months ago
- Autonomous GPU Kernel Generation via Deep Agents☆192Updated last week
- Code Repository of Evaluating Quantized Large Language Models☆137Updated last year
- Code for the AAAI 2024 Oral paper "OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Model…☆68Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆256Updated 4 months ago
- ☆37Updated last year
- ☆156Updated 10 months ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆25Updated last year
- Distributed MoE in a Single Kernel [NeurIPS '25]☆157Updated this week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆175Updated last year
- Building the Virtuous Cycle for AI-driven LLM Systems☆100Updated this week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆360Updated 5 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆59Updated 9 months ago
- ☆65Updated 8 months ago
- ☆125Updated 4 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆90Updated last year