fix: Adjust frontEnd thresholds #2288 #2290
Closed
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
biswapanda
requested review from
a team,
alec-flowers,
grahamking,
hhzhang16,
hutm,
ishandhanani,
julienmancuso,
mohammedabdulwahhab,
nealvaidya,
nnshah1,
piotrm-nvidia,
ptarasiewiczNV,
richardhuo-nv,
rmccorm4,
ryanolson,
tanmayv25 and
whoisj
as code owners
biswapanda
requested review from
GuanLuo,
PeaBrane,
jthomson04,
kkranen,
paulhendricks,
tedzhouhk and
tmonty12
as code owners
Contributor
|
Caution Review failedFailed to post review comments. WalkthroughThis update introduces substantial documentation restructuring, new deployment guides, and configuration improvements across multiple backend components. Notably, it adds Kubernetes deployment examples and guides for TRTLLM and vLLM, reorganizes and corrects support matrix and installation instructions, modularizes port allocation logic for the vLLM backend, and migrates engine configuration files to new formats. Several Dockerfiles and build scripts are updated for version consistency and improved health check tooling. The multimodal example documentation is removed, and Grove feature configuration in the operator is refactored to use a termination delay parameter with runtime detection. Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant EtcdClient
participant PortsModule
participant vLLMBackend
User->>vLLMBackend: Start backend with CLI args (--dynamo-port-min/max)
vLLMBackend->>PortsModule: Request port allocation block (tp_size)
PortsModule->>PortsModule: Bind and check port block availability
PortsModule->>EtcdClient: Reserve port block in ETCD with metadata
PortsModule-->>vLLMBackend: Return allocated port block
vLLMBackend->>vLLMBackend: Configure side channel and KV ports
vLLMBackend-->>User: Backend ready with reserved ports
sequenceDiagram
participant Operator
participant K8sAPI
participant GroveAPI
Operator->>K8sAPI: Discover API groups
K8sAPI-->>Operator: Return API groups
Operator->>Operator: Detect Grove availability
Operator->>Operator: Set Grove.Enabled and TerminationDelay
Operator->>K8sAPI: Deploy resources with Grove config (if available)
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Poem
Warning There were issues while running some tools. Please review the errors and either fix the tool's configuration or disable the tool if it's a critical failure. 🔧 golangci-lint (2.2.2)Error: can't load config: unsupported version of the configuration: "" See https://golangci-lint.run/product/migration-guide for migration instructions Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
mohammedabdulwahhab
requested changes
Aug 5, 2025
Contributor
There was a problem hiding this comment.
@biswapanda @atchernych I noticed that this already was merged ot main, but will this work? These values don't seem too reasonable to me as they give the worker 30 seconds to fully bootstrap.
Contributor
Author
|
This is not a release blocker for 04.0 closing the PR |
auto-merge was automatically disabled
August 5, 2025 06:05
Pull request was closed
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.
Overview:
Cherry-pick: #2288 (merged to main)
More reasonable values to avoid customer confusion (https://nvbugspro.nvidia.com/bug/5425651)
closes: https://nvbugspro.nvidia.com/bug/5425651
Summary by CodeRabbit
New Features
Bug Fixes
Documentation
Refactor
Chores