Merged
Conversation
facebook-github-bot
added
the
CLA Signed
dongwang218
reviewed
Apr 15, 2025
matrix/app_server/deploy_utils.py
Outdated
| if "max_replica" not in app: | ||
| app["max_replica"] = app["min_replica"] | ||
|
|
||
| if app_type == "llm": |
Contributor
There was a problem hiding this comment.
change to if app_type in ["llm", "sglang_llm"]
dongwang218
reviewed
Apr 15, 2025
Comment on lines
+344
to
+348
| async def check_health(self): | ||
| if self.healthy: | ||
| return {"status": "healthy"} | ||
| else: | ||
| raise RuntimeError("Replica unhealthy!") # Triggers Ray Serve restart |
dongwang218
approved these changes
Apr 15, 2025
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why ?
add a lora model example.
In this PR, we explicitly call init_static_loras() to load lora_request, this is due a change in vllm @ 0.7.0 vllm-project/vllm@ac2f3f7. Not sure why they made such change..
How ?
when deploy, need to specify lora-modules
e.g. {'lora-modules': 'sql-lora=/checkpoint/comem/huggingface_models/mistral_based_claim_extractor'}
and then in make_request, model="sql-lora"