#50 today
nguyentuongbachhy/lfm25-inference
Rust Library
A Rust + CUDA inference runtime for LFM2.5-1.2B-Instruct, focused on low-latency GPU inference, explicit memory management, paged KV caching, and measured kernel/runtime optimization.
Last active today
Created Aug 16, 2026
- Stars
- 8
- Today
- +8
- Forks
- 0
- Quality
- 85/100
- Momentum
- 18
First trending
Aug 16, 2026
first spotted on the list
Best rank
#50
highest position reached
Appearances
2
times on the trending list
Quality score
85
out of 100
Momentum
18
trend strength indicator
Star velocity
8.0
stars per day since creation
Activity — last 60 days
daily counts, collected every 6 hours- Stars
- Forks
- Merged PRs
- Issues
- Closed issues
Collecting activity data since launch — check back in a few days.
Star history
total stars per snapshotRank history
position on trending · lower is betterStars badge
Show current stars in your README or profile. Auto-updates every 6 hours.
Markdown
[](https://www.notionpulse.cc/repo/nguyentuongbachhy/lfm25-inference) HTML
<a href="https://www.notionpulse.cc/repo/nguyentuongbachhy/lfm25-inference"><img src="https://www.notionpulse.cc/api/badge/nguyentuongbachhy/lfm25-inference.svg" alt="nguyentuongbachhy/lfm25-inference stars badge" /></a> Repository of the Day
Repository of the Week
Repository of the Month
