Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix: Discard KV cache for last token before reusing prompt cache for prompt + suffix #79

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix: Discard KV cache for last token before reusing prompt cache for prompt + suffix #79

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6606949
Fix: Discard KV cache for last token before reusing prompt cache with…
sannat17 Oct 21, 2024
399268b
Show the difference between naively reusing prompt cache and using th…
sannat17 Oct 21, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
Fix: Discard KV cache for last token before reusing prompt cache with… 
… suffix added to prompt
  • Loading branch information
@sannat17
sannat17 committed Oct 21, 2024
commit 6606949bb0b42d534bec129897787aae7990b19a
2 changes: 2 additions & 0 deletions performance_optimization/prompt_reuse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@
inputs = tokenizer(INITIAL_PROMPT, return_tensors="pt").to("cuda")
with torch.no_grad():
prompt_cache = model(**inputs, past_key_values = prompt_cache).past_key_values
prompt_cache.key_cache = [x[:, :, :-1] for x in prompt_cache.key_cache]
prompt_cache.value_cache = [x[:, :, :-1] for x in prompt_cache.value_cache]


prompt = "Why are french people obsessed with french?"
Expand Down