casper-hansen / AutoAWQ_kernelsLinks
☆76Updated 8 months ago
Alternatives and similar repositories for AutoAWQ_kernels
Users that are interested in AutoAWQ_kernels are comparing it to the libraries listed below
Sorting:
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆137Updated 4 months ago
- ☆92Updated 4 months ago
- A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.☆175Updated 4 months ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆103Updated 4 months ago
- ☆195Updated 3 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆40Updated last month
- Standalone Flash Attention v2 kernel without libtorch dependency☆111Updated 10 months ago
- ☆74Updated 4 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆318Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 11 months ago
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆117Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆260Updated 3 weeks ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆142Updated this week
- The official implementation of the EMNLP 2023 paper LLM-FP4☆211Updated last year
- ⚡️FFPA: Extend FlashAttention-2 with Split-D, achieve ~O(1) SRAM complexity for large headdim, 1.8x~3x↑ vs SDPA. 🎉☆194Updated 2 months ago
- ☆31Updated 6 months ago
- Fast and memory-efficient exact attention☆83Updated this week
- KV cache compression for high-throughput LLM inference☆134Updated 6 months ago
- Reorder-based post-training quantization for large language model☆193Updated 2 years ago
- ☆75Updated 2 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆145Updated 2 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- ☆60Updated 3 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆113Updated last year
- Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.☆31Updated last week
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆225Updated 8 months ago
- ☆153Updated 2 years ago
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆169Updated this week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆123Updated 8 months ago
- ☆79Updated 6 months ago