fix: add a check for int32 indices in sampling.py by raayandhar · Pull Request #2127 · flashinfer-ai/flashinfer

raayandhar · 2025-11-21T08:09:35Z

📌 Description

New function to validate that the indices type, when provided, is int32. To close #2115.
There are now two separate functions doing checking in this file. I will move them to the C++ side later when I have some more bandwidth, probably after Thanksgiving. Just a short fix for now. You can close if you'd rather wait for that.

🔍 Related Issues

#2115

Relevant to the issue. Now running their code:

(flashinfer) raayan@uril-1:~/projects/flashinfer$ python test.py 
tensor([1, 1, 0, 0], device='cuda:0', dtype=torch.int32)
Traceback (most recent call last):
  File "/home/raayan/projects/flashinfer/test.py", line 15, in <module>
    incorrect_samples = flashinfer.sampling.top_k_top_p_sampling_from_logits(
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/raayan/projects/flashinfer/flashinfer/sampling.py", line 1031, in top_k_top_p_sampling_from_logits
    _check_indices_dtype(indices)
  File "/home/raayan/projects/flashinfer/flashinfer/sampling.py", line 487, in _check_indices_dtype
    raise ValueError(f"indices must have dtype torch.int32, got {indices.dtype}")
ValueError: indices must have dtype torch.int32, got torch.int64

🚀 Pull Request Checklist

Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete.

✅ Pre-commit Checks

I have installed pre-commit by running pip install pre-commit (or used your preferred method).
I have installed the hooks with pre-commit install.
I have run the hooks manually with pre-commit run --all-files and fixed any reported issues.

If you are unsure about how to set up pre-commit, see the pre-commit documentation.

🧪 Tests

Tests have been added or updated as needed.
All tests are passing (unittest, etc.).

Reviewer Notes

Summary by CodeRabbit

Improvements
- Enforced that indices passed to sampling operations must use int32, adding runtime validation before sampling.
Documentation
- Clarified docstrings to state the int32 requirement for indices parameters.
Tests
- Updated and expanded tests to cover the new dtype validation paths and related error cases.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

Signed-off-by: Raayan Dhar raayan.dhar@gmail.com <raayan.dhar@gmail.com>

gemini-code-assist · 2025-11-21T08:09:51Z

Summary of Changes

Hello @raayandhar, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces a crucial type validation for indices tensors within the sampling module, ensuring they are consistently torch.int32. This change directly resolves an existing issue where int64 indices could cause unexpected failures, thereby enhancing the robustness and reliability of the sampling operations across the codebase.

Highlights

Indices Type Validation: A new utility function, _check_indices_dtype, has been introduced to validate that indices tensors passed to sampling functions are of torch.int32 dtype. This addresses an issue where int64 indices could lead to runtime errors.
Integration of Type Check: The _check_indices_dtype function is now called within all relevant sampling functions (sampling_from_logits, sampling_from_probs, top_p_sampling_from_probs, top_k_sampling_from_probs, min_p_sampling_from_probs, top_k_top_p_sampling_from_logits, top_k_top_p_sampling_from_probs) to enforce the int32 requirement for indices.
Documentation Update: The docstrings for the indices parameter in several sampling functions have been updated to explicitly state the torch.int32 dtype requirement, improving clarity for developers.
New Test Case: A new test case has been added to test_sampling.py to specifically validate that a ValueError is raised when indices with torch.int64 dtype are provided to min_p_sampling_from_probs, ensuring the new validation works as expected.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

coderabbitai · 2025-11-21T08:09:55Z

Note

Other AI code review bot(s) detected

CodeRabbit has detected other AI code review bot(s) in this pull request and will avoid duplicating their findings in the review comments. This may lead to a less comprehensive review.

Walkthrough

Added an internal _check_indices_dtype(indices) validator enforcing torch.int32 for any provided indices tensor and invoked it at the start of multiple sampling entrypoints; docstrings were updated to state the dtype requirement and tests were adjusted to cover non-int32 rejection.

Changes

Cohort / File(s)	Summary
Sampling validation `flashinfer/sampling.py`	Added `_check_indices_dtype(indices)` to validate that `indices` tensors are `torch.int32`. Inserted calls to this validator at the start of sampling functions handling `logits`, `probs`, `top_p`, `top_k`, `min_p`, and combined `top_k/top_p` variants. Updated docstrings to document the `torch.int32` requirement.
Tests — sampling utils `tests/utils/test_sampling.py`	Renamed `test_check_tensor_param_min_p` → `test_tensor_validation_min_p`. Updated tests to pass float32 for `min_p` indicator where applicable and added assertions that non-int32 `indices` raise a `ValueError` about dtype; preserved batch-size mismatch checks.

Sequence Diagram(s)

sequenceDiagram
  autonumber
  participant Caller
  participant Sampling as Sampling Module
  participant Validator as _check_indices_dtype
  Caller->>Sampling: call sampling_fn(inputs, ..., indices)
  alt indices provided
    Sampling->>Validator: _check_indices_dtype(indices)
    alt dtype == int32
      Validator-->>Sampling: OK
      Sampling->>Sampling: proceed with sampling logic
      Sampling-->>Caller: return samples
    else dtype != int32
      Validator-->>Sampling: raise ValueError("indices must be torch.int32")
      Sampling-->>Caller: propagate ValueError
    end
  else no indices
    Sampling->>Sampling: proceed with sampling logic
    Sampling-->>Caller: return samples
  end

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Pay attention to the exact error message text in _check_indices_dtype() for clarity and test alignment.
Verify every sampling entrypoint that accepts indices calls the validator.
Confirm docstring updates match function signatures and test expectations.

Poem

🐰 I nibble bugs beneath the code's glow,
I check each index — int32, steady and slow.
No long sneaks past where the samples hop,
I guard the paths from quiet flop.
Hooray — clean dtype, onward we go! 🥕

Pre-merge checks and finishing touches

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change: adding validation for int32 dtype on indices in sampling.py functions.
Description check	✅ Passed	The description includes motivation (closing issue #2115), related issue link, and working example demonstrating the fix. However, it lacks explicit mention of the test additions beyond a checkbox.
Linked Issues check	✅ Passed	The PR directly addresses issue #2115 by implementing validation to reject indices with non-int32 dtypes, which prevents silent failures when long/int64 indices are used.
Out of Scope Changes check	✅ Passed	All changes are directly scoped to the objective: adding _check_indices_dtype validation function, applying it across sampling functions, updating docstrings, and adding corresponding tests.
Docstring Coverage	✅ Passed	Docstring coverage is 81.82% which is sufficient. The required threshold is 80.00%.

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment

📜 Recent review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 71e48ea and 214a7a9.

📒 Files selected for processing (1)

tests/utils/test_sampling.py (3 hunks)

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

GitHub Check: Deploy Docs

🔇 Additional comments (1)

tests/utils/test_sampling.py (1)

575-602: Revamped min-p tensor validation test looks correct and aligned with API semantics

Renaming to test_tensor_validation_min_p and switching the 2D and 0D min_p tensors to dtype=torch.float32 matches the intended “probability” semantics and keeps the error-path checks (rank and batch-size handling) intact. The scalar/1D success cases and the 2D/0D failure cases together give good coverage of the Python-side validation for min_p_sampling_from_probs.

Tip

📝 Customizable high-level summaries are now available in beta!

You can now customize how CodeRabbit generates the high-level summary in your pull requests — including its content, structure, tone, and formatting.

Provide your own instructions using the high_level_summary_instructions setting.
Format the summary however you like (bullet lists, tables, multi-section layouts, contributor stats, etc.).
Use high_level_summary_in_walkthrough to move the summary from the description to the walkthrough section.

Example instruction:

"Divide the high-level summary into five sections:

📝 Description — Summarize the main change in 50–60 words, explaining what was done.

📓 References — List relevant issues, discussions, documentation, or related PRs.

📦 Dependencies & Requirements — Mention any new/updated dependencies, environment variable changes, or configuration updates.

📊 Contributor Summary — Include a Markdown table showing contributions:
| Contributor | Lines Added | Lines Removed | Files Changed |

✔️ Additional Notes — Add any extra reviewer context.
Keep each section concise (under 200 words) and use bullet or numbered lists for clarity."

Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later.

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.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

gemini-code-assist

Code Review

This pull request correctly adds a check to ensure that the indices tensor, when provided, has a torch.int32 dtype. The new validation function _check_indices_dtype is properly integrated into the various sampling functions, and the docstrings have been updated accordingly. I have one suggestion to improve the clarity of the newly added test case.

Signed-off-by: Raayan Dhar raayan.dhar@gmail.com <raayan.dhar@gmail.com>

yzh119

It should be easy to support int64 indices for these kernels as well, but let's left them for future PRs.

## 📌 Description  Originally in this PR #1652 and #2127 we added better error messaging / prevent silent failures for wrong dtype / shape of tensors. However, it was on the python side when we can instead move to the C++ side (actually the `.cu` side, I guess). We already have various checks here via macros, so it is somewhat natural. ## 🔍 Related Issues See the issues in the PRs above.  ## 🚀 Pull Request Checklist Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete. ### ✅ Pre-commit Checks - [x] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [x] I have installed the hooks with `pre-commit install`. - [x] I have run the hooks manually with `pre-commit run --all-files` and fixed any reported issues. > If you are unsure about how to set up `pre-commit`, see [the pre-commit documentation](https://pre-commit.com/). ## 🧪 Tests - [x] Tests have been added or updated as needed. - [x] All tests are passing (`unittest`, etc.). ## Reviewer Notes   ## Summary by CodeRabbit * **Bug Fixes** * Native modules now perform stricter runtime validation of int index inputs and sampling-parameter shapes; some Python-level preflight checks were removed, deferring certain dtype/shape errors to lower-level code. * **Refactor** * Added a centralized, reusable validation helper for optional sampling parameters to unify checks. * **Tests** * Updated tests to expect different error types and more general error-message matching for the adjusted validation behavior. ✏️ Tip: You can customize this high-level summary in your review settings.  --------- Signed-off-by: Raayan Dhar raayan.dhar@gmail.com <raayan.dhar@gmail.com>

## 📌 Description  Originally in this PR flashinfer-ai#1652 and flashinfer-ai#2127 we added better error messaging / prevent silent failures for wrong dtype / shape of tensors. However, it was on the python side when we can instead move to the C++ side (actually the `.cu` side, I guess). We already have various checks here via macros, so it is somewhat natural. ## 🔍 Related Issues See the issues in the PRs above.  ## 🚀 Pull Request Checklist Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete. ### ✅ Pre-commit Checks - [x] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [x] I have installed the hooks with `pre-commit install`. - [x] I have run the hooks manually with `pre-commit run --all-files` and fixed any reported issues. > If you are unsure about how to set up `pre-commit`, see [the pre-commit documentation](https://pre-commit.com/). ## 🧪 Tests - [x] Tests have been added or updated as needed. - [x] All tests are passing (`unittest`, etc.). ## Reviewer Notes   ## Summary by CodeRabbit * **Bug Fixes** * Native modules now perform stricter runtime validation of int index inputs and sampling-parameter shapes; some Python-level preflight checks were removed, deferring certain dtype/shape errors to lower-level code. * **Refactor** * Added a centralized, reusable validation helper for optional sampling parameters to unify checks. * **Tests** * Updated tests to expect different error types and more general error-message matching for the adjusted validation behavior. ✏️ Tip: You can customize this high-level summary in your review settings.  --------- Signed-off-by: Raayan Dhar raayan.dhar@gmail.com <raayan.dhar@gmail.com>

## 📌 Description Based on this [comment](#2127 (review)) in #2127, we can add support for Int64 indices as well. I decided to do this using `IdType` like it is done in other files.  ## 🔍 Related Issues  ## 🚀 Pull Request Checklist Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete. ### ✅ Pre-commit Checks - [x] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [x] I have installed the hooks with `pre-commit install`. - [x] I have run the hooks manually with `pre-commit run --all-files` and fixed any reported issues. > If you are unsure about how to set up `pre-commit`, see [the pre-commit documentation](https://pre-commit.com/). ## 🧪 Tests - [x] Tests have been added or updated as needed. - [x] All tests are passing (`unittest`, etc.). Test results: ``` (flashinfer) raayan@uril-1:~/projects/flashinfer$ pytest tests/utils/test_sampling.py ============================================================= test session starts ============================================================= platform linux -- Python 3.12.3, pytest-9.0.2, pluggy-1.6.0 rootdir: /home/raayan/projects/flashinfer configfile: pytest.ini collected 1884 items tests/utils/test_sampling.py .......................................................................................................... [ 5%] ....................................................................................................................................... [ 12%] ....................................................................................................................................... [ 19%] ....................s..s..s..........................................................................sss........................sss.... [ 27%] ....................................................................................................................................... [ 34%] ..........................ssss................................ssss................................ssss................................s [ 41%] sss................................ssss................................ssss................................ssss........................ [ 48%] ........ssss................................ssss................................ssss................................ssss............... [ 55%] .................ssss................................ssss................................ssss................................ssss...... [ 62%] ..........................ssss................................ssss................................ssss................................s [ 70%] sss................................ssss................................ssss................................ssss........................ [ 77%] ........ssss................................ssss................................ssss................................ssss............... [ 84%] .................ssss.................................................................................................................. [ 91%] ........................................................sss............................................................................ [ 98%] ....................... [100%] ================================================ 1764 passed, 120 skipped in 546.33s (0:09:06) ================================================ (flashinfer) raayan@uril-1:~/projects/flashinfer$ ``` ## Reviewer Notes  --------- Signed-off-by: raayandhar <raayan.dhar@gmail.com>

## 📌 Description New function to validate that the indices type, when provided, is `int32`. To close flashinfer-ai#2115. There are now two separate functions doing checking in this file. I will move them to the C++ side later when I have some more bandwidth, probably after Thanksgiving. Just a short fix for now. You can close if you'd rather wait for that.  ## 🔍 Related Issues flashinfer-ai#2115  Relevant to the issue. Now running their code: ``` (flashinfer) raayan@uril-1:~/projects/flashinfer$ python test.py tensor([1, 1, 0, 0], device='cuda:0', dtype=torch.int32) Traceback (most recent call last): File "/home/raayan/projects/flashinfer/test.py", line 15, in <module> incorrect_samples = flashinfer.sampling.top_k_top_p_sampling_from_logits( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/raayan/projects/flashinfer/flashinfer/sampling.py", line 1031, in top_k_top_p_sampling_from_logits _check_indices_dtype(indices) File "/home/raayan/projects/flashinfer/flashinfer/sampling.py", line 487, in _check_indices_dtype raise ValueError(f"indices must have dtype torch.int32, got {indices.dtype}") ValueError: indices must have dtype torch.int32, got torch.int64 ``` ## 🚀 Pull Request Checklist Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete. ### ✅ Pre-commit Checks - [x] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [x] I have installed the hooks with `pre-commit install`. - [x] I have run the hooks manually with `pre-commit run --all-files` and fixed any reported issues. > If you are unsure about how to set up `pre-commit`, see [the pre-commit documentation](https://pre-commit.com/). ## 🧪 Tests - [x] Tests have been added or updated as needed. - [x] All tests are passing (`unittest`, etc.). ## Reviewer Notes   ## Summary by CodeRabbit * **Improvements** * Enforced that indices passed to sampling operations must use int32, adding runtime validation before sampling. * **Documentation** * Clarified docstrings to state the int32 requirement for indices parameters. * **Tests** * Updated and expanded tests to cover the new dtype validation paths and related error cases. ✏️ Tip: You can customize this high-level summary in your review settings.  --------- Signed-off-by: Raayan Dhar raayan.dhar@gmail.com <raayan.dhar@gmail.com>

## 📌 Description  Originally in this PR flashinfer-ai#1652 and flashinfer-ai#2127 we added better error messaging / prevent silent failures for wrong dtype / shape of tensors. However, it was on the python side when we can instead move to the C++ side (actually the `.cu` side, I guess). We already have various checks here via macros, so it is somewhat natural. ## 🔍 Related Issues See the issues in the PRs above.  ## 🚀 Pull Request Checklist Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete. ### ✅ Pre-commit Checks - [x] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [x] I have installed the hooks with `pre-commit install`. - [x] I have run the hooks manually with `pre-commit run --all-files` and fixed any reported issues. > If you are unsure about how to set up `pre-commit`, see [the pre-commit documentation](https://pre-commit.com/). ## 🧪 Tests - [x] Tests have been added or updated as needed. - [x] All tests are passing (`unittest`, etc.). ## Reviewer Notes   ## Summary by CodeRabbit * **Bug Fixes** * Native modules now perform stricter runtime validation of int index inputs and sampling-parameter shapes; some Python-level preflight checks were removed, deferring certain dtype/shape errors to lower-level code. * **Refactor** * Added a centralized, reusable validation helper for optional sampling parameters to unify checks. * **Tests** * Updated tests to expect different error types and more general error-message matching for the adjusted validation behavior. ✏️ Tip: You can customize this high-level summary in your review settings.  --------- Signed-off-by: Raayan Dhar raayan.dhar@gmail.com <raayan.dhar@gmail.com>

## 📌 Description  Originally in this PR flashinfer-ai/flashinfer#1652 and flashinfer-ai/flashinfer#2127 we added better error messaging / prevent silent failures for wrong dtype / shape of tensors. However, it was on the python side when we can instead move to the C++ side (actually the `.cu` side, I guess). We already have various checks here via macros, so it is somewhat natural. ## 🔍 Related Issues See the issues in the PRs above.  ## 🚀 Pull Request Checklist Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete. ### ✅ Pre-commit Checks - [x] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [x] I have installed the hooks with `pre-commit install`. - [x] I have run the hooks manually with `pre-commit run --all-files` and fixed any reported issues. > If you are unsure about how to set up `pre-commit`, see [the pre-commit documentation](https://pre-commit.com/). ## 🧪 Tests - [x] Tests have been added or updated as needed. - [x] All tests are passing (`unittest`, etc.). ## Reviewer Notes   ## Summary by CodeRabbit * **Bug Fixes** * Native modules now perform stricter runtime validation of int index inputs and sampling-parameter shapes; some Python-level preflight checks were removed, deferring certain dtype/shape errors to lower-level code. * **Refactor** * Added a centralized, reusable validation helper for optional sampling parameters to unify checks. * **Tests** * Updated tests to expect different error types and more general error-message matching for the adjusted validation behavior. ✏️ Tip: You can customize this high-level summary in your review settings.  --------- Signed-off-by: Raayan Dhar raayan.dhar@gmail.com <raayan.dhar@gmail.com>

## 📌 Description Based on this [comment](flashinfer-ai/flashinfer#2127 (review)) in flashinfer-ai/flashinfer#2127, we can add support for Int64 indices as well. I decided to do this using `IdType` like it is done in other files.  ## 🔍 Related Issues  ## 🚀 Pull Request Checklist Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete. ### ✅ Pre-commit Checks - [x] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [x] I have installed the hooks with `pre-commit install`. - [x] I have run the hooks manually with `pre-commit run --all-files` and fixed any reported issues. > If you are unsure about how to set up `pre-commit`, see [the pre-commit documentation](https://pre-commit.com/). ## 🧪 Tests - [x] Tests have been added or updated as needed. - [x] All tests are passing (`unittest`, etc.). Test results: ``` (flashinfer) raayan@uril-1:~/projects/flashinfer$ pytest tests/utils/test_sampling.py ============================================================= test session starts ============================================================= platform linux -- Python 3.12.3, pytest-9.0.2, pluggy-1.6.0 rootdir: /home/raayan/projects/flashinfer configfile: pytest.ini collected 1884 items tests/utils/test_sampling.py .......................................................................................................... [ 5%] ....................................................................................................................................... [ 12%] ....................................................................................................................................... [ 19%] ....................s..s..s..........................................................................sss........................sss.... [ 27%] ....................................................................................................................................... [ 34%] ..........................ssss................................ssss................................ssss................................s [ 41%] sss................................ssss................................ssss................................ssss........................ [ 48%] ........ssss................................ssss................................ssss................................ssss............... [ 55%] .................ssss................................ssss................................ssss................................ssss...... [ 62%] ..........................ssss................................ssss................................ssss................................s [ 70%] sss................................ssss................................ssss................................ssss........................ [ 77%] ........ssss................................ssss................................ssss................................ssss............... [ 84%] .................ssss.................................................................................................................. [ 91%] ........................................................sss............................................................................ [ 98%] ....................... [100%] ================================================ 1764 passed, 120 skipped in 546.33s (0:09:06) ================================================ (flashinfer) raayan@uril-1:~/projects/flashinfer$ ``` ## Reviewer Notes  --------- Signed-off-by: raayandhar <raayan.dhar@gmail.com>

raayandhar added 2 commits November 20, 2025 23:00

add _check_indices_dtype in sampling.py

0b7ed2f

Signed-off-by: Raayan Dhar raayan.dhar@gmail.com <raayan.dhar@gmail.com>

add a test

71e48ea

Signed-off-by: Raayan Dhar raayan.dhar@gmail.com <raayan.dhar@gmail.com>

raayandhar requested review from aleozlx, cyx-6, nvmbreughe, wenscarl and yzh119 as code owners November 21, 2025 08:09

gemini-code-assist Bot reviewed Nov 21, 2025

View reviewed changes

Comment thread tests/utils/test_sampling.py Outdated

address comment

214a7a9

Signed-off-by: Raayan Dhar raayan.dhar@gmail.com <raayan.dhar@gmail.com>

yzh119 approved these changes Nov 22, 2025

View reviewed changes

yzh119 merged commit 5e11004 into flashinfer-ai:main Nov 22, 2025
4 checks passed

raayandhar mentioned this pull request Dec 2, 2025

feat: C++ side tensor validation #2160

Merged

5 tasks

raayandhar mentioned this pull request Jan 2, 2026

feat: IdType indices in sampling kernels #2281

Merged

5 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

fix: add a check for int32 indices in sampling.py#2127

fix: add a check for int32 indices in sampling.py#2127
yzh119 merged 3 commits intoflashinfer-ai:mainfrom
raayandhar:user/rdhar/int32_sampling_indices

raayandhar commented Nov 21, 2025 •

edited by coderabbitai Bot

Loading

Uh oh!

gemini-code-assist Bot commented Nov 21, 2025

Uh oh!

coderabbitai Bot commented Nov 21, 2025 •

edited

Loading

Other AI code review bot(s) detected

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

Uh oh!

yzh119 left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

raayandhar commented Nov 21, 2025 • edited by coderabbitai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

📌 Description

🔍 Related Issues

🚀 Pull Request Checklist

✅ Pre-commit Checks

🧪 Tests

Reviewer Notes

Summary by CodeRabbit

Uh oh!

gemini-code-assist Bot commented Nov 21, 2025

Summary of Changes

Highlights

Footnotes

Uh oh!

coderabbitai Bot commented Nov 21, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Other AI code review bot(s) detected

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Poem

Pre-merge checks and finishing touches

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

yzh119 left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

raayandhar commented Nov 21, 2025 •

edited by coderabbitai Bot

Loading

coderabbitai Bot commented Nov 21, 2025 •

edited

Loading