-
Notifications
You must be signed in to change notification settings - Fork 753
fix: Fix NIXL 0.3.1 build #1561
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
Conversation
WalkthroughThe changes update the Changes
Poem
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. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Actionable comments posted: 0
🧹 Nitpick comments (2)
lib/llm/src/block_manager/block/transfer/nixl.rs (2)
140-155: Unnecessary double boxing – dropBox::pinfor a leaner future
Box::new(Box::pin(async move { … }))allocates twice and returns
Box<Pin<Box<_>>>, which is larger than needed.
Because the returned trait object is required to beUnpin, you can
simply box theasyncblock – it isUnpinby default.- Ok(Box::new(Box::pin(async move { + Ok(Box::new(async move { let nixl_agent = nixl_agent_arc .as_ref() .as_ref() .expect("NIXL agent not found"); @@ } - }))) + }))This removes one heap allocation and clarifies the intent.
146-150: Busy-wait loop: expose poll intervalA hard-coded 5 ms sleep is easy to forget and might be sub-optimal on
different hardware. Consider:const POLL_INTERVAL: Duration = Duration::from_millis(5); … tokio::time::sleep(POLL_INTERVAL).await;or making it configurable via
TransferContext.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (1)
Cargo.lockis excluded by!**/*.lock
📒 Files selected for processing (2)
lib/llm/Cargo.toml(1 hunks)lib/llm/src/block_manager/block/transfer/nixl.rs(1 hunks)
⏰ Context from checks skipped due to timeout of 90000ms (5)
- GitHub Check: Mirror Repository to GitLab
- GitHub Check: pre-merge-rust (lib/runtime/examples)
- GitHub Check: pre-merge-rust (.)
- GitHub Check: pre-merge-rust (lib/bindings/python)
- GitHub Check: Build and Test - vllm
🔇 Additional comments (2)
lib/llm/Cargo.toml (1)
83-85: To ensure the pinned commit truly exists, let’s verify it via GitHub’s API:#!/usr/bin/env bash # Check if the specific commit exists in the GitHub repo status=$(curl -s -o /dev/null -w "%{http_code}" \ https://api.github.com/repos/ai-dynamo/nixl/commits/a7c654d46a14cd5ce635cc8c02433d71df93dedf) echo "HTTP status: $status" if [ "$status" = "200" ]; then echo "✅ Commit exists and is reachable." else echo "❌ Commit not found (status $status)." exit 1 filib/llm/src/block_manager/block/transfer/nixl.rs (1)
120-122: ```shell
#!/usr/bin/env bashSearch the entire repo for the XferDescList definition and its
newimplementationrg --context 5 "struct XferDescList" -n .
rg --context 5 "impl XferDescList" -n .
find . -type f -iname "xfer_desc_list.rs"</details> </blockquote></details> </details> <!-- This is an auto-generated comment by CodeRabbit for review status -->
nv-anants
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks John! After merge, please add a cherry pick PR for release/0.3.1 branch as well
|
@nv-anants Release branch MR opened here: #1571 |
Fixes a issue that kept
nixl-syspinned at 0.3.0, even though we're using NIXL 0.3.1. See #1517 (comment)Summary by CodeRabbit
Chores
Refactor