@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / cff8991a50
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 15, 17:15 UTC

[Docs][V1] Optimize diagrams in prefix caching design (#15716)

simpx committed Mar 29, 2025 at 11:33 UTC cff8991a50dd35c2cb9d2e6d3446a0051cac144a
6 files changed
docs/source/assets/design/v1/prefix_caching/example-time-1.png
Binary files a/docs/source/assets/design/v1/prefix_caching/example-time-1.png and b/docs/source/assets/design/v1/prefix_caching/example-time-1.png differ
docs/source/assets/design/v1/prefix_caching/example-time-3.png
Binary files a/docs/source/assets/design/v1/prefix_caching/example-time-3.png and b/docs/source/assets/design/v1/prefix_caching/example-time-3.png differ
docs/source/assets/design/v1/prefix_caching/example-time-4.png
Binary files a/docs/source/assets/design/v1/prefix_caching/example-time-4.png and b/docs/source/assets/design/v1/prefix_caching/example-time-4.png differ
docs/source/assets/design/v1/prefix_caching/example-time-5.png
Binary files a/docs/source/assets/design/v1/prefix_caching/example-time-5.png and b/docs/source/assets/design/v1/prefix_caching/example-time-5.png differ
docs/source/assets/design/v1/prefix_caching/example-time-6.png
Binary files a/docs/source/assets/design/v1/prefix_caching/example-time-6.png and b/docs/source/assets/design/v1/prefix_caching/example-time-6.png differ
docs/source/assets/design/v1/prefix_caching/example-time-7.png
Binary files a/docs/source/assets/design/v1/prefix_caching/example-time-7.png and b/docs/source/assets/design/v1/prefix_caching/example-time-7.png differ