[NIXL][XPU] Use np.uint64 for pointer/length arrays in disaggregation KV transfer#24188
Merged
Conversation
Jianhong-Zhang
requested review from
ByronHsu,
ShangmingCai and
hnyls2002
as code owners
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
ShangmingCai
approved these changes
May 1, 2026
Collaborator
ShangmingCai
left a comment
ShangmingCai
left a comment
There was a problem hiding this comment.
Looks good.
cc: @ishandhanani
Collaborator
|
check ci first and then try to update test cases (on intel gpu devices). |
github-actions
Bot
added
the
documentation
Jianhong-Zhang
force-pushed
the
dtype
branch
2 times, most recently
from
b6a1021 to
5587a3b
Compare
Contributor
Author
|
/tag-and-rerun-ci |
mingfeima
approved these changes
May 6, 2026
| [OpenAI Completions API](https://docs.sglang.io/basic_usage/openai_api_completions.html) | ||
| and sent via the command line (e.g. using `curl`) or via your own script. | ||
|
|
||
| ## Prefill-Decode (P/D) Disaggregation on Intel XPU |
Collaborator
There was a problem hiding this comment.
Suggested change
| ## Prefill-Decode (P/D) Disaggregation on Intel XPU | |
| ## [Experimental] Prefill-Decode (P/D) Disaggregation on Intel XPU |
… KV transfer Intel XPU device addr. pointers can exceed np.int64 range (bit 63 set), causing overflows and incorrect arithmetic when using numpy. This patch ensures all pointer and length arrays in the NIXL disaggregation backend are cast to np.uint64 up front, preventing overflow and dtype promotion issues during numpy operations. This is required for XPU safety and correctness, and does not affect device addr. at low bit set. - Cast src_data_ptrs, dst_data_ptrs, and item_lens to np.uint64 in _send_kvcache_generic - Ensures pointer arithmetic is safe for high-bit XPU addresses - Adds/clarifies comments explaining the rationale - Adds unit test for P/D disagg on XPU - updates xpu.md for P/D disagg on XPU test steps
LucQueen
pushed a commit
to LucQueen/sglang
that referenced
this pull request
May 12, 2026
5 tasks
zijiexia
added a commit
to zijiexia/sglang
that referenced
this pull request
Jun 4, 2026
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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.
Intel XPU device addr. pointers can exceed np.int64 range (bit 63 set), causing overflows and incorrect arithmetic when using numpy. This patch ensures all pointer and length arrays in the NIXL disaggregation backend are cast to np.uint64 up front, preventing overflow and dtype promotion issues during numpy operations. This is required for XPU safety and correctness, and does not affect device addr. at low bit set.