Skip to content
GitHub Explorer

massif-01/vllm_auto_tune

View on GitHub ↗Related repositories →

Automated vLLM server parameter tuning tool. Finds optimal max-num-seqs and max-num-batched-tokens to maximize throughput. Includes presets for Llama/Qwen/Mixtral, batch processing, result analysis with visualizations, and environment checks. Supports TPU/GPU with latency constraints.

active 2025-10-30 → 2025-11-23 (UTC)

Partial coverage11,325 / 12,146 hourly files (93%) · 2 absent upstream · 818 failed, retryable2025-03-22 → 2026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
3
Pushes
0
Pull requests
1
Issues
0
Stars
1
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 25 days from 2025-10-30 to 2025-11-23. Pushes: 0 total, peak 0 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Stars: 1 total, peak 1 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
massif-011010

Recent activity

Latest issues, pull requests and releases

  • Pull request#1massif-012025-10-30 10:25

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1 stars here means stars gained during the window, not the repo's star count.