Add prompt_to_lora_id_mapping adjustment in fix_prompts() on release/v1.19 #250
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
quic-jouachen
force-pushed
the
finitelorax_fixprompts_fix_rel1.19
branch
2 times, most recently
from
88a6eb9 to
2447937
Compare
quic-jouachen
force-pushed
the
finitelorax_fixprompts_fix_rel1.19
branch
3 times, most recently
from
ab4c6fb to
bd54026
Compare
Signed-off-by: Jou-An Chen <[email protected]>
quic-jouachen
force-pushed
the
finitelorax_fixprompts_fix_rel1.19
branch
from
bd54026 to
e146e06
Compare
ochougul
reviewed
Jan 31, 2025
| @@ -311,7 +332,7 @@ def cloud_ai_100_exec_kv( | |||
| """ | |||
| batch_size, ctx_len, full_batch_size = get_compilation_dims(qpc_path) | |||
| prompt: List[str] = get_input_prompts(prompt, prompts_txt_file_path) | |||
| prompt = fix_prompts(prompt, batch_size, full_batch_size) | |||
| prompt, prompt_to_lora_id_mapping = fix_prompts(prompt, batch_size, prompt_to_lora_id_mapping, full_batch_size) | |||
There was a problem hiding this comment.
I think we should separate the function to fix prompt_to_lora_id_mapping and call it only when it's value is other than None.
For this release branch this is okay. But for Mainline let's change it.
Signed-off-by: Onkar Chougule <[email protected]>
quic-rishinr
approved these changes
Jan 31, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Same as PR#242
This is regarding the issue reported in issue#251
The finite lorax feature failed to execute when the number of prompts provided is less than the full batch size. The solution involves applying the same adjustment strategy for
prompt_to_lora_id_mappingas used forpromptin thefix_prompts()function located inQEfficient/generation/text_generation_inference.py.