[GH-ISSUE #1318] Figure in the book doesn't match the text #4373

Open
opened 2026-04-19 12:23:40 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @gustaf-hammarberg on GitHub (Apr 10, 2026).
Original GitHub issue: https://github.com/harvard-edge/cs249r_book/issues/1318

Originally assigned to: @profvjreddi on GitHub.

Figure 14 in the Model Optimizations chapter doesn't match the text:

Image

Figure 14: Quantization Impact: Moving from FP32 to INT8 reduces inference time by up to 4 times while decreasing model size by a factor of 4, making models more efficient for resource-constrained environments.

Originally created by @gustaf-hammarberg on GitHub (Apr 10, 2026). Original GitHub issue: https://github.com/harvard-edge/cs249r_book/issues/1318 Originally assigned to: @profvjreddi on GitHub. Figure 14 in the Model Optimizations chapter doesn't match the text: <img width="535" height="305" alt="Image" src="https://github.com/user-attachments/assets/2042b251-854a-4e7a-9cb8-2757b75cc961" /> Figure 14: Quantization Impact: Moving from FP32 to INT8 reduces inference time by up to 4 times while decreasing model size by a factor of 4, making models more efficient for resource-constrained environments.
GiteaMirror added the area: booktype: errata labels 2026-04-19 12:23:40 -05:00
Author
Owner

@profvjreddi commented on GitHub (Apr 13, 2026):

Thank you, @gustaf-hammarberg -- appreciate you bringing this issue to my attention. I am looking into it now; I was traveling, so pardon the delay.

<!-- gh-comment-id:4236633247 --> @profvjreddi commented on GitHub (Apr 13, 2026): Thank you, @gustaf-hammarberg -- appreciate you bringing this issue to my attention. I am looking into it now; I was traveling, so pardon the delay.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/cs249r_book#4373