Grouped-Query Attention memory (#874)

* GQA memory

* remove redundant code

* update links

* update
This commit is contained in:
Sebastian Raschka
2025-10-11 08:44:19 -05:00
committed by GitHub
parent b8e12e1dd1
commit c814814d72
7 changed files with 1114 additions and 0 deletions

3
.gitignore vendored
View File

@@ -11,6 +11,9 @@ appendix-D/01_main-chapter-code/3.pdf
appendix-E/01_main-chapter-code/loss-plot.pdf
ch04/04_gqa/kv_bytes_vs_context_length.pdf
ch04/04_gqa/savings_vs_n_kv_groups.pdf
ch05/01_main-chapter-code/loss-plot.pdf
ch05/01_main-chapter-code/temperature-plot.pdf
ch05/01_main-chapter-code/the-verdict.txt