Llama-Vision: Enable tracing, refactor generation code #15005
Merged
Conversation
This file contains 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
…ashDecode are different
…ommit goes back to nlp_tms to create/concat heads.
…porting mask shapes required by non-causal FlashDecode
…tch > 1. WIP, since these changes have now broken the full model and demos
…=1, nonworking for batch>1.
…ep and model execution with ttnn tensors.
…reation and device tensor transformations. Enabled tracing in simple_vision_demo with an easy trace function
…ing generation pipelines.
cglagovichTT
force-pushed
the
cglagovich/14519_noopt
branch
from
60fdc3a to
31944db
Compare
cglagovichTT
requested review from
yieldthought,
mtairum,
uaydonat,
ayerofieiev-tt,
dmakoviichuk-tt,
cfjchu,
TT-BrianLiu,
blozano-tt and
ttmchiou
as code owners
cfjchu
approved these changes
Nov 13, 2024
ttmchiou
approved these changes
Nov 14, 2024
ayerofieiev-tt
approved these changes
Nov 14, 2024
cglagovichTT
changed the title
mtairum
approved these changes
Nov 14, 2024
5 tasks
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Outdated suggestions cannot be applied.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.
Ticket
#14519
What's changed
This PR changes the Llama-Vision interface to make it easier to add batch>1 inference, continuous batching, and vLLM integration.
vision_generator.pysimple_vision_demo.pyfor easy testing and e2e perf measurementChecklist