[Core] Modulize prepare input and attention metadata builder #6596
+409
−298
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
|
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, please make sure to run full CI as it is required to merge (or just use auto-merge). To run full CI, you can do one of these:
🚀 |
comaniac
force-pushed
the
refactor-prepare-input
branch
from
fb00532 to
8a2c134
Compare
comaniac
force-pushed
the
refactor-prepare-input
branch
from
8a2c134 to
0d9d62e
Compare
comaniac
force-pushed
the
refactor-prepare-input
branch
from
a7719d9 to
f386f69
Compare
xjpang
pushed a commit
to xjpang/vllm
that referenced
this pull request
Jul 24, 2024
gnpinkert
pushed a commit
to gnpinkert/vllm
that referenced
this pull request
Jul 26, 2024
cduk
pushed a commit
to cduk/vllm-pascal
that referenced
this pull request
Aug 6, 2024
| tokens = [seq_data.get_last_token_id()] | ||
|
|
||
| inter_data.seq_lens[seq_idx] = seq_len | ||
| inter_data.orig_seq_lens[seq_idx] = seq_len |
There was a problem hiding this comment.
Is it a bug? seq_len might be truncated according to line 300: seq_len = min(seq_len, context_len + token_chunk_size)
kylesayrs
pushed a commit
to neuralmagic/vllm
that referenced
this pull request
Aug 17, 2024
Alvant
pushed a commit
to compressa-ai/vllm
that referenced
this pull request
Oct 26, 2024
…oject#6596) Signed-off-by: Alvant <[email protected]>
KuntaiDu
pushed a commit
to KuntaiDu/vllm
that referenced
this pull request
Nov 20, 2024
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Outdated suggestions cannot be applied.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.
This PR further refactors model input builder and attention metadata builder to be more modulized and maintainable. Specifically:
attention_matadata_builder._add_seq_groupprivate, and let each attention metadata builder handle by itself. This removes the ugly argument list and provides more flexibility for each attention backend to customizeadd_seq_group.cc @Yard1 @rkooo567