xlite-dev/Awesome-LLM-Inference
๐A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.๐
License & maintenance
GPL-3.0 is a copyleft license: products that include or modify it may have to publish their code.
Last code push 2 months ago.