A minimal implementation of vllm.
☆73Jul 27, 2024Updated last year
Alternatives and similar repositories for vllmini
Users that are interested in vllmini are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An simple pytorch implementation of Flash MultiHead Attention☆22Feb 5, 2024Updated 2 years ago
- ☆89Jan 23, 2025Updated last year
- a minimal cache manager for PagedAttention, on top of llama3.☆144Aug 26, 2024Updated last year
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆329Jun 10, 2025Updated 11 months ago
- ☆10Nov 16, 2024Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆32May 20, 2026Updated last week
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆32Jun 14, 2024Updated last year
- Compression for Foundation Models☆35Jul 21, 2025Updated 10 months ago
- transformer which using numpy，vision transformer of VIT, MNIST testset precision = 97.2%，mutil-attention, patch embed, position embed, fu…☆12Mar 4, 2026Updated 2 months ago
- [ICML‘25] Official code for paper "Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training an…☆13Apr 17, 2025Updated last year
- pytorch Implement for "A Point Set Generation Network for 3D Object Reconstruction from a Single Image"☆10Jan 5, 2020Updated 6 years ago
- ☆13Jan 22, 2025Updated last year
- Official Implementation of APB (ACL 2025 main Oral) and Spava (ACL 2026 main).☆37Apr 6, 2026Updated last month
- SOTA Learning-augmented Systems☆37May 21, 2022Updated 4 years ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Implementation for IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs (ICLR 2024).☆25Feb 22, 2026Updated 3 months ago
- ☆25Dec 30, 2025Updated 5 months ago
- An MLIR-based toy DL compiler for TVM Relay.☆62Oct 16, 2022Updated 3 years ago
- The goal of the OSSCI Fleet is to provide a central mechanism to enable test automation, batch job scheduling, and developer access to a …☆13Apr 28, 2026Updated last month
- A throughput-oriented high-performance serving framework for LLMs☆961Mar 29, 2026Updated 2 months ago
- Official code for the paper "HEXA-MoE: Efficient and Heterogeneous-Aware MoE Acceleration with Zero Computation Redundancy"☆15Mar 6, 2025Updated last year
- This is the repo for remote direct memory introspection.☆25Jun 21, 2023Updated 2 years ago
- ☆14Mar 9, 2023Updated 3 years ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆24Nov 21, 2024Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Connect6 (Korean: 육목) for Python.☆11May 15, 2017Updated 9 years ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆74Sep 8, 2024Updated last year
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆391Apr 13, 2025Updated last year
- Multi-agent system for booking appointments and generating PDF invoices☆13Jul 16, 2025Updated 10 months ago
- Sparsity support for PyTorch☆39Mar 22, 2025Updated last year
- ☆13Sep 23, 2021Updated 4 years ago
- A PyTorch reimplementation of Local Implicit Grid Representations for 3D Scenes☆17Jul 21, 2021Updated 4 years ago
- Prototyp MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism☆31Apr 4, 2025Updated last year
- A Triton-only attention backend for vLLM☆25Mar 17, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆16Aug 19, 2024Updated last year
- GPTQ inference Triton kernel☆322May 18, 2023Updated 3 years ago
- hep-analysis aims to reproduce the traditional data-analysis workflow in high-energy physics using Python.☆10May 22, 2018Updated 8 years ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆284Mar 6, 2025Updated last year
- Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning☆25May 12, 2025Updated last year
- A simple template for TensorFlow's highly efficient CudnnLSTM module☆11Jun 8, 2018Updated 7 years ago
- ☆19Jan 27, 2025Updated last year