xlite-dev/Awesome-LLM-Inference

๐Ÿ“šA curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.๐ŸŽ‰

5.5k
Stars
438
Forks
55.5
Radar Score
Stable
Momentum

Scoring Breakdown

Impact87.1
Velocity27.6
Health43.8

Growth Metrics

7-Day Stars
+8
30-Day Stars
+33
Acceleration
0.97x
Language
Python

Why it ranks

Modest but positive momentum.

Multimodal AI ยท vision-languageTop 100% globallyLast push 58d ago+8 stars / 7d+33 stars / 30d
View on GitHub