add block_size arg to chat api #2986
Draft
+11
−1
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
RunningLeon
reviewed
Jan 7, 2025
| @@ -256,6 +259,12 @@ def chat(args): | |||
| if backend == 'pytorch': | |||
| from lmdeploy.messages import PytorchEngineConfig | |||
| from lmdeploy.pytorch.chat import run_chat | |||
| block_size = 64 # default block size | |||
| if args.device == 'camb': | |||
There was a problem hiding this comment.
hi, camb is not in the choices of --device,
lmdeploy/lmdeploy/cli/utils.py
Line 380 in c6c25ae
There was a problem hiding this comment.
Yes, camb is on WIP, will be merged as part of dlinfer backend in the future, we can apply this PR after camb main work is merged
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Outdated suggestions cannot be applied.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.
Motivation
Since camb device backend only supports block_size=16 for paged_attention relevant ops, we need to enable control of block_size.
This PR add
cache_block_seq_lenarg parser to lmdeploy chat API.After this PR, we can use
lmdeploy chat /Shanghai_AI_Laboratory/internlm2_5-7b --backend pytorch --device camb --cache-block-seq-len 16to chat on camb device