INT-FlashAttention2024 / INT-FlashAttentionLinks
☆82Updated 8 months ago
Alternatives and similar repositories for INT-FlashAttention
Users that are interested in INT-FlashAttention are comparing it to the libraries listed below
Sorting:
- ☆53Updated last year
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆60Updated last month
- LLM Inference with Microscaling Format☆31Updated 10 months ago
- ☆64Updated 5 months ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆111Updated last week
- PyTorch bindings for CUTLASS grouped GEMM.☆123Updated 4 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆59Updated 6 months ago
- Quantized Attention on GPU☆44Updated 10 months ago
- DeeperGEMM: crazy optimized version☆71Updated 5 months ago
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆170Updated last week
- ☆35Updated last year
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆116Updated last year
- ☆115Updated last month
- ☆72Updated last year
- Implement Flash Attention using Cute.☆96Updated 9 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆150Updated 4 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆118Updated last year
- llama INT4 cuda inference with AWQ☆55Updated 8 months ago
- ☆99Updated 4 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆141Updated last month
- ☆151Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- ☆50Updated 4 months ago
- Code implementation of GPTAQ (https://arxiv.org/abs/2504.02692)☆65Updated 2 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆245Updated last week
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- ☆98Updated last year
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆37Updated 7 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 2 months ago
- ☆143Updated 7 months ago