collect-workloads

Community

Auto-collect ML workloads from SGLang inferences.

AuthorRockyeast
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Auto-collect real-world workloads produced by SGLang inferences using FlashInfer logging, then sanitize results for inclusion in the flashinfer-trace dataset and preparation for PR submissions.

Core Features & Use Cases

  • Auto-detect and collect workloads from definitions across op_types using SGLang + FlashInfer Level 10 logging.
  • Sanitize per-call dumps into flashinfer-trace JSONL and safetensors for compact, reproducible workloads.
  • Default to sglang mode for end-to-end collection, with a direct mode fallback when FlashInfer APIs are not wired into SGLang.
  • Map raw dumps to the flashinfer-trace schema, align plan/run dumps, and prepare metadata for PRs to HuggingFace.
  • Output is ready for per-definition HuggingFace PRs, including workload JSONL, safetensors, and definition metadata.

Quick Start

Run the collect_workloads.py script in sglang mode with your target definitions and a flashinfer-trace directory to start automatic collection, sanitization, and optional PR submission.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: collect-workloads
Download link: https://github.com/Rockyeast/flashinfer-trace-dev/archive/main.zip#collect-workloads

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.