Sign in

Repository Index

47,133 repositories indexed

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters

Filters

Clear all filters

73–96 of 225 · Most stars

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

Translated【A common used C++ & Python DAG framework】 A general-purpose, third-party-dependency-free, cross-platform parallel computing framework based on flow graphs, listed in awesome-cpp. Welcome to star & fork & discuss

The fastest unified streaming SQL Engine in a single C++ binary. ⚡ Millisecond latency. 100+ GB/s throughput. Continuously compute stateful context from streams, logs, metrics, events, and CDC.

A full spaCy pipeline and models for scientific/biomedical documents.

  • scientific-documents
  • spacy
  • custom-pipes
  • nlp

Build data pipelines with SQL and Python, ingest data from different sources, add quality checks, and build end-to-end flows.

A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.

Cookbook for Node on FHIR and the clinical Meteor.js build pipeline. Create FDA, HIPPA, and HL7 compliant Javascript/Node applications!