An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
☆282Jul 16, 2025Updated last year
Alternatives and similar repositories for fp6_llm
Users that are interested in fp6_llm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆350Jul 2, 2024Updated 2 years ago
- ☆20Sep 28, 2024Updated 2 years ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆772Aug 6, 2025Updated last year
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆541Nov 26, 2024Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆867Mar 6, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- The official implementation of the EMNLP 2023 paper LLM-FP4☆227Dec 15, 2023Updated 2 years ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,174Sep 4, 2024Updated 2 years ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆130Jul 13, 2024Updated 2 years ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- A Easy-to-understand TensorOp Matmul Tutorial☆459Mar 5, 2026Updated 8 months ago
- ☆65Apr 26, 2025Updated last year
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆395Apr 13, 2025Updated last year
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆438Nov 20, 2025Updated 11 months ago
- Fast low-bit matmul kernels in Triton☆491Oct 1, 2026Updated last month
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆193Jan 28, 2025Updated last year
- ☆173Mar 9, 2023Updated 3 years ago
- Kernel Library for Large Headdim Attention (64~1024, BF16/FP8/FP4), 1.5x~15x↑ vs PyTorch SDPA.☆346Updated this week
- Microsoft Automatic Mixed Precision Library☆635Dec 1, 2025Updated 11 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆162Aug 21, 2025Updated last year
- GPTQ inference Triton kernel☆321May 18, 2023Updated 3 years ago
- A Quirky Assortment of CuTe Kernels☆1,189Oct 30, 2026Updated last week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆129Mar 18, 2026Updated 7 months ago
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆178Nov 26, 2025Updated 11 months ago
- ☆271Jul 11, 2024Updated 2 years ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆436Aug 13, 2024Updated 2 years ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆357Mar 10, 2026Updated 7 months ago
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆142May 16, 2024Updated 2 years ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆414Jul 10, 2025Updated last year
- ☆92Jan 23, 2025Updated last year
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,601Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆269Aug 9, 2025Updated last year
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆119Oct 28, 2026Updated last week
- ☆210May 5, 2025Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆724Aug 13, 2024Updated 2 years ago
- ☆202Aug 9, 2026Updated 2 months ago
- ☆194May 11, 2026Updated 5 months ago
- [WIP] Better (FP8) attention for Hopper☆33Aug 21, 2026Updated 2 months ago