mit-han-lab / omniserveLinks
[MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
☆770Updated 7 months ago
Alternatives and similar repositories for omniserve
Users that are interested in omniserve are comparing it to the libraries listed below
Sorting:
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆916Updated last year
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆698Updated 2 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆433Updated 11 months ago
- A throughput-oriented high-performance serving framework for LLMs☆909Updated this week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆389Updated last year
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆567Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆439Updated this week
- ☆343Updated last year
- A low-latency & high-throughput serving engine for LLMs☆431Updated last week
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆329Updated last month
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆335Updated 8 months ago
- Perplexity GPU Kernels☆497Updated last month
- LLM KV cache compression made easy☆660Updated last week
- Fast low-bit matmul kernels in Triton☆385Updated this week
- A powerful toolkit for compressing large models including LLM, VLM, and video generation models.☆593Updated 2 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆266Updated 3 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,186Updated last week
- FlagGems is an operator library for large language models implemented in the Triton Language.☆703Updated this week
- Materials for learning SGLang☆618Updated 3 weeks ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆144Updated 2 months ago
- Applied AI experiments and examples for PyTorch☆299Updated 2 months ago
- This repository contains integer operators on GPUs for PyTorch.☆220Updated 2 years ago
- A collection of memory efficient attention operators implemented in the Triton language.☆282Updated last year
- Disaggregated serving system for Large Language Models (LLMs).☆709Updated 6 months ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆460Updated 6 months ago
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆179Updated last week
- Zero Bubble Pipeline Parallelism☆433Updated 5 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆248Updated last week
- Microsoft Automatic Mixed Precision Library☆626Updated last year