Blog post about how to optimize LLMs for memory and speed (#1473)

* correct ((

* [LLMs] Getting most out of LLMS

* finish

* finish

* Fix

* finish

* finish

* finish

* finish

* Apply suggestions from code review

Co-authored-by: Younes Belkada <[email protected]>
Co-authored-by: Joao Gante <[email protected]>

* improve

---------

Co-authored-by: Younes Belkada <[email protected]>
Co-authored-by: Joao Gante <[email protected]>

Author: 3 people

_blog.yml

@@ -2777,7 +2777,7 @@
     - collaboration
     - diffusers
     - diffusion
-    
+
 - local: safecoder-vs-closed-source-code-assistants
   title: "SafeCoder vs. Closed-source Code Assistants"
   author: julsimon
@@ -2818,3 +2818,13 @@
     - diffusion
     - diffusers
     - text-to-image
+
+# - local: optimize-llm
+#   title: "Optimizing your LLM in production"
+#   author: patrickvonplaten
+#   thumbnail: /blog/assets/163_optimize_llm/self_attn_tokens.png
+#   date: Sep 18, 2023
+#   tags:
+#     - nlp
+#     - research
+#     - LLM