-
Notifications
You must be signed in to change notification settings - Fork 28
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat: upgrade vllm backend and refactor deployment #854
Draft
justinthelaw
wants to merge
115
commits into
main
Choose a base branch
from
835-upgrade-vllm-for-gptq-bfloat16-inferencing
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Draft
feat: upgrade vllm backend and refactor deployment #854
justinthelaw
wants to merge
115
commits into
main
from
835-upgrade-vllm-for-gptq-bfloat16-inferencing
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
…gptq-bfloat16-inferencing
…gptq-bfloat16-inferencing
…ded during loud builds
…nicorns/leapfrogai into feat-make-silent-parallel-build
…gptq-bfloat16-inferencing
…gptq-bfloat16-inferencing
2 tasks
justinthelaw
force-pushed
the
835-upgrade-vllm-for-gptq-bfloat16-inferencing
branch
from
September 17, 2024 01:10
1ac3cba
to
6593fbb
Compare
Blocked by #1038, wait until that is merged and re-test this branch locally with the new vLLM E2E. |
…gptq-bfloat16-inferencing
justinthelaw
added
the
blocked 🛑
Something needs to happen before this issues is worked
label
Sep 17, 2024
justinthelaw
removed
the
blocked 🛑
Something needs to happen before this issues is worked
label
Sep 19, 2024
This was
linked to
issues
Sep 19, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Labels
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.
OVERVIEW
See #835 for more details on rationale and findings. Also related to #623.
IMPORTANT NOTE: there are still ongoing AsyncLLMEngineDead and RoPE scaling + Ray issues upstream that may prevent us from upgrading past
0.4.x
.BREAKING CHANGES:
volumeMount
for runtime injection and modificationconfig.yaml
envFrom
for runtime injection and modification.env
ZARF_CONFIG
is used to define create-time adn deploy-time variables for (e.g.,MODEL_REPO_ID
,ENFORCE_EAGER
)config.yaml
configuration method for local development and testingCHANGES:
packages/vllm/README.md
)QUANTIZATION
options to existing configuration fieldADDITIONAL CONTEXT
The default model is still Synthia-7b, until #976 is resolved. The below description is only being kept for future context: