factor out a SequenceTable from PageTable/DecodeState, #1256
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
# Conflicts: # src/levanter/inference/engine.py # src/levanter/layers/attention.py # src/levanter/main/sample_lm.py # src/levanter/models/llama.py # tests/inference/test_engine.py
dlwh
commented
Oct 15, 2025
| decode_state = decode_state.assign_seq( | ||
| local_slot_id=slot_val, | ||
| tokens=work.prompt_tokens["seq", i], | ||
| seq_len=prompt_len, |
Member
Author
There was a problem hiding this comment.
we actually want it to start out as 0 and get set during prefill
rjpower
approved these changes
Oct 15, 2025
| outputs = _DecodeOutputs.init( | ||
| max_tokens=gen_state.decode_state.max_seqs * 2, | ||
| max_seqs=gen_state.decode_state.max_seqs, | ||
| max_tokens=decode_state.max_seqs * 2, |
Collaborator
There was a problem hiding this comment.
RP: review this in more detail.
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Outdated suggestions cannot be applied.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.
There were a bunch of things in DecodeState that duplicated what was in PageTable, and it was a big mess. Now it is a somewhat smaller mess.