xlite-dev/Awesome-LLM-Inference

Awesome-LLM-Inference

βœ… Recently maintained

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

5,542Stars
443Forks
+47-day stars

Python Β· GPL-3.0 Β· Last push 2026-10-20

Official repository & installation β†—

Star history

2025-09-292026-11-02
View historical data
DateStars
2026-10-045,514
2026-10-055,515
2026-10-065,516
2026-10-075,516
2026-10-085,517
2026-10-095,517
2026-10-105,518
2026-10-115,521
2026-10-125,522
2026-10-135,525
2026-10-145,526
2026-10-155,527
2026-10-165,528
2026-10-175,528
2026-10-185,528
2026-10-195,530
2026-10-205,532
2026-10-215,533
2026-10-225,534
2026-10-235,535
2026-10-245,536
2026-10-255,538
2026-10-265,538
2026-10-275,538
2026-10-285,538
2026-10-295,540
2026-10-305,540
2026-10-315,541
2026-11-015,542
2026-11-025,542

Get the project

git clone https://github.com/xlite-dev/Awesome-LLM-Inference.git

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.