PiPNN 2/6: add numerical kernels by SeliMeli · Pull Request #1287 · microsoft/DiskANN

weiyaoluo (SeliMeli) · 2026-07-29T11:51:48Z

Summary

Add GEMM-backed distance computation and SIMD top-k selection for PiPNN behind the opt-in diskann/pipnn feature.

The numerical layer supports two operations:

Partition assignment: rank sampled leaders for each point and return their local IDs.
Leaf neighbor selection: compute each unordered point pair once and update both endpoints’ neighbor lists, returning local IDs and distances.

This is part 2 of the PiPNN stack. Recursive graph construction integrates these kernels in #1290.

Design

Separate metric computation from neighbor selection. Metric implementations handle L2, cosine, normalized cosine, and inner product. Partition leaders retain metric-specific norms for reuse across point stripes. Kernels choose which distance slices
to process; the shared TopK implementation handles SIMD loading, threshold filtering, scalar tails, and sorted insertion.

Reuse each leaf distance for both endpoints. New diskann-linalg helpers compute or accumulate the lower triangle of a Gram matrix using faer. Leaf selection scans the strict lower triangle, excludes self-neighbors, and shares each loaded distance
block between both endpoint updates.

Specialize common top-k capacities. Capacities 1–10 use compile-time specialization to enable insertion-loop unrolling; larger capacities use the runtime path. Typical partition fanouts are 10 and 3, and typical leaf-neighbor counts are 2 or 3.
Architecture-specific selection runs through diskann-wide at the TopK entry points.

Keep storage reusable. TopK borrows caller-owned candidate buffers. Kernels manage distance and ranking scratch without exposing SIMD block types to their callers.

The linear-algebra helpers validate matrix shapes and size-product overflow.

Copilot

Pull request overview

This PR adds the first set of PiPNN “kernel” building blocks to the DiskANN Rust workspace: SIMD-accelerated top‑k selection for partition assignment and leaf neighbor selection, along with supporting SIMD division and a new lower-triangular A·Aᵀ helper in diskann-linalg.

Changes:

Add a new diskann-pipnn crate with partition_kernel and leaf_kernel implementations plus extensive correctness tests and Criterion benchmarks.
Extend diskann-wide to support Div on relevant f32 SIMD types (native, doubled, and scalar/emulated) and add a corresponding division test macro.
Add diskann_linalg::sgemm_aat_lower (lower-triangle-only AAT) and wire new crate/tests/CI/mutants exclusions into the workspace.

Reviewed changes

Copilot reviewed 26 out of 27 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
diskann-wide/src/test_utils/ops.rs	Adds `test_div!` macro to validate lane-wise SIMD division correctness.
diskann-wide/src/emulated.rs	Adds `Div` for scalar/emulated `Emulated<f32, N, A>` to support division in scalar dispatch.
diskann-wide/src/doubled.rs	Adds `Div` for `Doubled<T>` to support composite SIMD widths.
diskann-wide/src/arch/x86_64/v4/f32x8_.rs	Adds AVX `Div` op mapping + division tests.
diskann-wide/src/arch/x86_64/v4/f32x4_.rs	Adds SSE `Div` op mapping + division tests.
diskann-wide/src/arch/x86_64/v4/f32x16_.rs	Adds AVX-512 `Div` op mapping + division tests.
diskann-wide/src/arch/x86_64/v3/f32x8_.rs	Adds AVX `Div` op mapping + division tests for V3.
diskann-wide/src/arch/x86_64/v3/f32x4_.rs	Adds SSE `Div` op mapping + division tests for V3.
diskann-wide/src/arch/x86_64/v3/f32x16_.rs	Adds division tests for the f32x16 V3 path (likely via doubled composition).
diskann-wide/src/arch/aarch64/f32x4_.rs	Adds Neon `Div` op mapping + division tests.
diskann-wide/src/arch/aarch64/f32x2_.rs	Adds Neon `Div` op mapping + division tests.
diskann-pipnn/tests/partition_kernel.rs	New integration tests for partition top‑k dispatch correctness and edge cases.
diskann-pipnn/tests/leaf_kernel.rs	New integration tests for leaf neighbor top‑k dispatch correctness and edge cases.
diskann-pipnn/src/partition_kernel/tests.rs	New unit tests comparing scalar reference vs runtime dispatch and metric contracts.
diskann-pipnn/src/partition_kernel.rs	New partition-assignment distance + top‑k kernel with validation and SIMD dispatch.
diskann-pipnn/src/lib.rs	New crate root exporting PiPNN kernel modules.
diskann-pipnn/src/leaf_kernel/tests.rs	New unit tests for scalar reference parity and workspace behavior.
diskann-pipnn/src/leaf_kernel.rs	New fused lower-triangle leaf neighbor kernel with SIMD dispatch and workspace support.
diskann-pipnn/Cargo.toml	Defines new `diskann-pipnn` crate, dev-deps, and benches.
diskann-pipnn/benches/kernels.rs	Adds benchmarks for partition top‑k, lower AAT, leaf top‑k, and full leaf workflow.
diskann-linalg/tests/sgemm_aat_lower.rs	New tests for lower-triangle AAT behavior and validation errors.
diskann-linalg/src/lib.rs	Adds public `sgemm_aat_lower` API with dimension checks.
diskann-linalg/src/faer.rs	Implements `sgemm_aat_lower_impl` using Faer triangular matmul.
Cargo.toml	Adds `diskann-pipnn` to workspace members and workspace dependencies.
Cargo.lock	Records the new `diskann-pipnn` package entry.
.github/workflows/ci.yml	Adds `diskann-pipnn` to CI test package lists.
.cargo/mutants.toml	Adds mutation-test exclusions for kernel code paths and equivalent transformations.

Comments suppressed due to low confidence (2)

diskann-pipnn/src/leaf_kernel.rs:651

Same issue as the L2 arm: using max_simd for lower clamping can erase NaNs on the Scalar/Emulated backend, making NaN distances rankable. Clamp with lt_simd + select to preserve NaNs consistently.

        Metric::CosineNormalized => {
            let distance = F::splat(arch, 1.0) - dot;
            zero.max_simd(distance)
        }

diskann-pipnn/src/leaf_kernel.rs:664

The cosine path also uses zero.max_simd(distance) for clamping, which can collapse NaNs to zero on the Scalar/Emulated backend (via f32::max). That contradicts the comment about preserving non-rankable NaNs and can change output ordering. Prefer an lt_simd + select clamp here as well.

            let distance = one - cosine;
            // Comparisons with NaN are false, so this explicit lower clamp
            // preserves non-rankable NaNs while matching the existing PiPNN
            // distance formulas for finite values.
            zero.max_simd(distance)

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot

Pull request overview

Copilot reviewed 26 out of 27 changed files in this pull request and generated no new comments.

Codecov Comments Bot (codecov-commenter) · 2026-07-30T08:42:36Z

Codecov Report

❌ Patch coverage is 99.10448% with 9 lines in your changes missing coverage. Please review.
✅ Project coverage is 92.72%. Comparing base (600c2b9) to head (166ac25).
⚠️ Report is 23 commits behind head on main.

Files with missing lines	Patch %	Lines
diskann/src/graph/pipnn/leaf_kernel.rs	98.01%	3 Missing ⚠️
diskann/src/graph/pipnn/topk.rs	98.88%	3 Missing ⚠️
diskann/src/graph/pipnn/partition_kernel.rs	98.71%	2 Missing ⚠️
diskann/src/graph/pipnn/leaf_metric.rs	98.57%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1287      +/-   ##
==========================================
+ Coverage   91.55%   92.72%   +1.17%     
==========================================
  Files         521      533      +12     
  Lines      100302   104113    +3811     
==========================================
+ Hits        91828    96540    +4712     
+ Misses       8474     7573     -901

Flag	Coverage Δ
miri	`92.72% <99.10%> (+1.17%)`	⬆️
unittests	`92.67% <99.10%> (+1.43%)`	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files with missing lines	Coverage Δ
diskann-linalg/src/faer.rs	`100.00% <100.00%> (ø)`
diskann-linalg/src/lib.rs	`99.72% <100.00%> (+0.03%)`	⬆️
diskann/src/graph/pipnn/mod.rs	`100.00% <100.00%> (ø)`
diskann/src/graph/pipnn/partition_metric.rs	`100.00% <100.00%> (ø)`
diskann/src/graph/pipnn/simd.rs	`100.00% <100.00%> (ø)`
diskann/src/graph/pipnn/leaf_metric.rs	`98.57% <98.57%> (ø)`
diskann/src/graph/pipnn/partition_kernel.rs	`98.71% <98.71%> (ø)`
diskann/src/graph/pipnn/leaf_kernel.rs	`98.01% <98.01%> (ø)`
diskann/src/graph/pipnn/topk.rs	`98.88% <98.88%> (ø)`

... and 180 files with indirect coverage changes

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Copilot

Pull request overview

Copilot reviewed 26 out of 27 changed files in this pull request and generated no new comments.

Comments suppressed due to low confidence (2)

diskann-pipnn/src/partition_kernel/tests.rs:20

The PartitionTopK contract for Metric::L2 expects leader_scales to contain squared leader norms (see docs and distance(Metric::L2, ..) test). This helper currently populates unsquared norms, which makes the test data inconsistent with the public API contract and could hide contract-related bugs.

    let leader_scales = match metric {
        Metric::L2 => (0..leaders).map(|leader| (leader + 1) as f32).collect(),
        Metric::Cosine => (0..leaders)
            .map(|leader| {

diskann-pipnn/src/partition_kernel.rs:61

InvalidFanout’s error message says the maximum is {maximum}, but validation also rejects fanout > leaders. When leaders < maximum this message is misleading (it implies the only limit is {maximum}). Consider spelling out both constraints in the message so callers immediately see why it failed.

    #[error("invalid fanout {fanout} for {leaders} leaders; maximum is {maximum}")]

Copilot

Pull request overview

Copilot reviewed 25 out of 26 changed files in this pull request and generated no new comments.

Suppressed comments (1)

diskann-pipnn/src/partition_kernel.rs:294

For Metric::Cosine, NaN norms currently produce a finite distance (1.0) because denominator.gt_simd(0) is false for NaN, so the lane falls back to cosine = 0. That makes NaN-derived pairs/leaders “rankable”, which contradicts the module’s stated NaN-rejection behavior and differs from diskann-vector cosine semantics (NaN norms propagate to a NaN similarity/distance). Consider explicitly preserving NaN denominators so the resulting distance stays NaN and is ignored by insert_topk.

        let denominator = row_norm * leader_norm;
        let valid = denominator.gt_simd(zero);
        let safe_denominator = valid.select(denominator, one);
        let cosine = valid.select(dot / safe_denominator, zero);
        one - cosine

juchen-ms (partychen)

Nice work overall. I found one correctness issue in the cosine handling that should be resolved before merge. The remaining comments are mostly about reducing duplicated or unsafe code and tightening the API contracts.

Aditya Krishnan (arkrishn94)

Thanks Weiyao, this is progress from the previous mega-PR. I still have some big-picture comments (we covered most of these offline) -

Documentation: As I mentioned, we need thorough documentation in the diskann-pipnn crate. The main modules, partition_kernel and leaf_kernel need documentation up top, highlighting the main structures and how they are used - e.g. process_rows_binary/unary and nearest_leaders. Similarly with process_pairs_simd_* and nearest_leaf_neighbors
Testing: I am concerned about the lack of testing for partition_kernel.rs and leaf_kernel.rs.
- I notice some e2e integration tests but these kernels should be thoroughly tested, sweeping different input parameters, architectures and edge cases. This is especially needed given the amount of unsafe code.
- That brings me to miri - there should be miri tests too.
- I'm curious why are the tests in a separate submodule to the main files (for partition_kernel.rs and leaf_kernel.rs)? Let's try to keep tests along with the code being tested.
Criterion: Since criterion is not a standard part of our library for benchmarking, let us not introduce it for this crate.
Kernel dispatch: I left comments about you're disptaching the kernels, please take a look.

Copilot

Pull request overview

Copilot reviewed 26 out of 27 changed files in this pull request and generated no new comments.

Suppressed comments (2)

diskann-pipnn/src/partition_kernel/tests.rs:19

PartitionTopK::leader_scales is documented as "squared leader norms for L2" (and cosine uses unsquared norms), but this test helper feeds unsquared values for the L2 case. That makes the test data inconsistent with the public contract and can mask mistakes in distance computation. Consider squaring the L2 norms here so the tests exercise the intended inputs.

    let leader_scales = match metric {
        Metric::L2 => (0..leaders).map(|leader| (leader + 1) as f32).collect(),
        Metric::Cosine => (0..leaders)

diskann-pipnn/src/partition_kernel.rs:252

For the L2 path, the SIMD chunk uses mul_add_simd (fused multiply-add) but the scalar tail uses norm - 2.0 * dot (non-fused). This can introduce small rounding differences between SIMD and tail elements, which can change ordering/tie behavior right at SIMD-width boundaries. Use f32::mul_add for the scalar tail so both paths compute the same value shape.

                |dot, norm| F::splat(arch, -2.0).mul_add_simd(dot, norm),
                |dot, norm| norm - 2.0 * dot,

weiyaoluo (SeliMeli) · 2026-08-03T07:02:19Z

weiyaoluo (@SeliMeli) please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
@microsoft-github-policy-service agree [company="{your company}"]
Options:

(default - no company specified) I have sole ownership of intellectual property rights to my Submissions and I am not making Submissions in the course of work for my employer.
@microsoft-github-policy-service agree
(when company given) I am making Submissions in the course of work for my employer (or my employer has intellectual property rights in my Submissions by contract or applicable law). I have permission from my employer to make Submissions and enter into this Agreement on behalf of my employer. By signing below, the defined term “You” includes me and my employer.
@microsoft-github-policy-service agree company="Microsoft"
Contributor License Agreement

@microsoft-github-policy-service agree company="Microsoft"

Keep width dispatch and SIMD distance blocks inside TopK. Reuse the same row storage for replacement and dual updates, and retain the measured unfilled-result path. Consolidate tests around reachable kernel behavior, independent output oracles, and workspace reuse.

Remove unreachable empty-kernel smoke cases and duplicate delegated checks. Keep point replacement fixtures at a fixed leader count, combine cosine formula and multi-row checks, and exercise rectangular AAT inputs.

Keep partition selection thresholds local and initialize reusable leaf state explicitly. Kernels own candidate storage across updates.

Enter the architecture scope per TopK operation with explicit buffer arguments so kernels only traverse rows. Preserve const capacity inside the feature boundary to keep sorted insertion specialized in release.

Copilot

🟡 Changes recommended

Both kernels perform unchecked distance-matrix size multiplication before reaching the new overflow validation.

Get a fresh assessment by requesting another Copilot review.

Review details

Files reviewed: 14/15 changed files
Comments generated: 2
Review effort level: Balanced

Aditya Krishnan (arkrishn94)

Thanks Weiyao.

I'm especially concerned about the coverage of the tests for the kernels - e.g. I don't see the happy paths being sufficiently tested over enough dimensions and widths. I also notice that the tests in partition_kernel and leaf_kernel don't exercise all metrics for the happy paths.
In terms of documentation, I have a slightly hard time following what exactly update_dual_top_k and update_many in topk.rs are supposed to be doing. I think topk.rs needs better documentation to describe the places the functions are used and what exactly they are doing.

Aditya Krishnan (arkrishn94) · 2026-09-16T01:32:31Z

+/// Specialize small capacities 1..=10; larger capacities use the runtime path.
+/// Typical partition K is 10 or 3, and leaf K is 3 or 2.
+/// The width is evaluated once. The body has ordinary block control flow.
+macro_rules! with_topk {


I'm not sure why you need this macro. If the goal here is to support using a topk value instantiated based on const/runtime width, this is not a extensible way to do it. It is hard to read/parse too. Why not just bubble the K const up higher so it can be passed?

replaced with visitor trait

Aditya Krishnan (arkrishn94) · 2026-09-16T02:46:38Z

+/// Default SIMD representation used by both PiPNN ranking kernels.
+///
+/// This alias is the single build-time width selection.
+type DefaultVector<A> = <A as Architecture>::f32x16;


Remind me, are we fixing the width to 16 across architectures? Is this reasonable for Neon?

NEON support seems not a priority for now. 16 works well on both avx2 and avx512, will keep this fixed for now. added todo comment for neon supporting

Check complete metric matrices and count/width ranking grids. Keep ranking and distance tolerances separate. Clarify test names and reusable-state fixtures. Run GEMM-backed tests natively and keep them out of Miri.

Name the dual-update test and dispatcher after their entry point. Record pending Neon width validation.

Wei Wu (wuw92) · 2026-09-18T03:26:43Z

 /// Default SIMD representation used by both PiPNN ranking kernels.
 ///
 /// This alias is the single build-time width selection.
+///


Use Github issue to track instead of todo in code.

PiPNN callers already bound or check their matrix shapes. Keep the shared constructor change and its tests outside this PR.

The merge with main enables clippy::allow_attributes. Use one scoped dead-code expectation until graph construction wires the kernels.

weiyaoluo (SeliMeli) requested review from a team and a lite review from Copilot July 29, 2026 11:51

Copilot started reviewing on behalf of weiyaoluo (SeliMeli) July 29, 2026 11:52 View session

Copilot AI reviewed Jul 29, 2026

View reviewed changes

Comment thread diskann-pipnn/src/leaf_kernel.rs Outdated

Comment thread diskann-pipnn/src/partition_kernel/tests.rs Outdated

weiyaoluo (SeliMeli) changed the title ~~Pipnn stack/01 kernels~~ PiPNN 1/6: add numerical kernels Jul 29, 2026

weiyaoluo (SeliMeli) mentioned this pull request Jul 29, 2026

Superseded by #1315: extract shared RobustPrune #1288

Merged

Copilot AI review requested due to automatic review settings July 30, 2026 08:26

weiyaoluo (SeliMeli) force-pushed the pipnn-stack/01-kernels branch from e204cb9 to b046174 Compare July 30, 2026 08:26

Copilot started reviewing on behalf of weiyaoluo (SeliMeli) July 30, 2026 08:27 View session

Copilot AI reviewed Jul 30, 2026

View reviewed changes

Copilot AI review requested due to automatic review settings July 30, 2026 08:55

Copilot started reviewing on behalf of weiyaoluo (SeliMeli) July 30, 2026 08:55 View session

Copilot AI reviewed Jul 30, 2026

View reviewed changes

Copilot AI review requested due to automatic review settings July 31, 2026 04:24

weiyaoluo (SeliMeli) force-pushed the pipnn-stack/01-kernels branch from 8fb4e92 to 20ab8a0 Compare July 31, 2026 04:24

Copilot started reviewing on behalf of weiyaoluo (SeliMeli) July 31, 2026 04:24 View session

Copilot AI reviewed Jul 31, 2026

View reviewed changes

juchen-ms (partychen) reviewed Jul 31, 2026

View reviewed changes

Comment thread diskann-pipnn/src/leaf_kernel.rs Outdated

Wei Wu (wuw92) reviewed Jul 31, 2026

View reviewed changes

juchen-ms (partychen) previously requested changes Jul 31, 2026

View reviewed changes

Aditya Krishnan (arkrishn94) reviewed Jul 31, 2026

View reviewed changes

Aditya Krishnan (arkrishn94) reviewed Aug 1, 2026

View reviewed changes

Comment thread diskann-pipnn/src/leaf_kernel.rs Outdated

Aditya Krishnan (arkrishn94) reviewed Aug 1, 2026

View reviewed changes

Comment thread diskann-pipnn/src/leaf_kernel.rs Outdated

Aditya Krishnan (arkrishn94) reviewed Aug 1, 2026

View reviewed changes

Comment thread diskann-pipnn/src/leaf_kernel.rs Outdated

Copilot AI review requested due to automatic review settings August 3, 2026 02:18

Copilot started reviewing on behalf of weiyaoluo (SeliMeli) August 3, 2026 02:18 View session

Copilot AI reviewed Aug 3, 2026

View reviewed changes

Copilot AI review requested due to automatic review settings August 3, 2026 10:49

Wei Wu (wuw92) reviewed Sep 8, 2026

View reviewed changes

Comment thread diskann/src/graph/pipnn/simd.rs Outdated

Comment thread diskann/src/graph/pipnn/leaf_kernel.rs Outdated

Comment thread diskann/src/graph/pipnn/simd.rs Outdated

Comment thread diskann/src/graph/pipnn/simd.rs

weiyaoluo (SeliMeli) added 6 commits September 8, 2026 09:16

refactor(pipnn): move distance blocks to topk

927ceb6

test(pipnn): simplify partition row rejection

5ef1097

refactor(pipnn): merge SIMD schema traits

f803283

test(pipnn): focus coverage on live contracts

4a3aed7

Remove unreachable empty-kernel smoke cases and duplicate delegated checks. Keep point replacement fixtures at a fixed leader count, combine cosine formula and multi-row checks, and exercise rectangular AAT inputs.

refactor(pipnn): borrow top-k buffers per call

dc10909

Keep partition selection thresholds local and initialize reusable leaf state explicitly. Kernels own candidate storage across updates.

Wei Wu (wuw92) reviewed Sep 10, 2026

View reviewed changes

Comment thread .github/workflows/nightly.yml

Comment thread diskann/src/graph/pipnn/topk.rs Outdated

Comment thread diskann/src/graph/pipnn/topk.rs Outdated

weiyaoluo (SeliMeli) added 3 commits September 10, 2026 06:32

fix(pipnn): keep SIMD scope inside top-k

78f5e95

Enter the architecture scope per TopK operation with explicit buffer arguments so kernels only traverse rows. Preserve const capacity inside the feature boundary to keep sorted insertion specialized in release.

fix(ci): run relocated top-k tests under Miri

c627be8

perf(pipnn): specialize top-k widths through ten

6a8d13e

Wei Wu (wuw92) approved these changes Sep 10, 2026

View reviewed changes

refactor(pipnn): make insertion capacity explicit

acda584

Copilot AI reviewed Sep 15, 2026

View reviewed changes

Comment thread diskann/src/graph/pipnn/leaf_kernel.rs

Comment thread diskann/src/graph/pipnn/partition_kernel.rs

Aditya Krishnan (arkrishn94) reviewed Sep 16, 2026

View reviewed changes

weiyaoluo (SeliMeli) added 7 commits September 16, 2026 07:45

refactor(pipnn): model top-k width with types

5e4c08a

refactor(pipnn): localize insertion slicing

08c2fba

refactor(pipnn): name top-k update directions

1bc033d

test(pipnn): cover numerical kernel matrices

fa560c3

Check complete metric matrices and count/width ranking grids. Keep ranking and distance tolerances separate. Clarify test names and reusable-state fixtures. Run GEMM-backed tests natively and keep them out of Miri.

refactor(pipnn): simplify workspace access

d0f048d

Name the dual-update test and dispatcher after their entry point. Record pending Neon width validation.

test(pipnn): clarify neighbor selection cases

4e75562

test(pipnn): rewrite numerical kernel contracts

d3ae858

Wei Wu (wuw92) reviewed Sep 18, 2026

View reviewed changes

weiyaoluo (SeliMeli) added 6 commits September 18, 2026 07:06

refactor(pipnn): dispatch TopK with a visitor

4690241

refactor(pipnn): reuse fast vector norms

34722b2

test(linalg): share lower-product assertions

4c97081

test(linalg): trim redundant GEMM shapes

5b853e0

refactor(pipnn): defer matrix view hardening

9660547

PiPNN callers already bound or check their matrix shapes. Keep the shared constructor change and its tests outside this PR.

fix(pipnn): expect unwired kernels in PR2

166ac25

The merge with main enables clippy::allow_attributes. Use one scoped dead-code expectation until graph construction wires the kernels.

Conversation

weiyaoluo (SeliMeli) commented Jul 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Design

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Codecov Comments Bot (codecov-commenter) commented Jul 30, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

juchen-ms (partychen) left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Aditya Krishnan (arkrishn94) left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

weiyaoluo (SeliMeli) commented Aug 3, 2026

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

weiyaoluo (SeliMeli) commented Jul 29, 2026 •

edited

Loading

Codecov Comments Bot (codecov-commenter) commented Jul 30, 2026 •

edited

Loading

juchen-ms (partychen) left a comment •

edited

Loading

weiyaoluo (SeliMeli) Sep 16, 2026 •

edited

Loading

Aditya Krishnan (arkrishn94) Sep 16, 2026 •

edited

Loading