New Features
- Added support for returning top-k token log probabilities during generation.
- Introduced a logprobs parameter in sampling settings to request N best logprobs per step (N ≥ 1), lifting the previous restriction of only 1.
- Responses now include per-token top-k logprobs with ranks for each generation step.
Tests
- Added a unit test to validate structure, length, ranking, and ordering of returned top-k logprobs.

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR FollowsTRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (seetest instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run/bot [-h|--help] to print this help message.

See details below for each supported subcommand.

run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]

Launch build/test pipelines. All previously running jobs will be killed.

--reuse-test (optional)pipeline-id(OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.

--disable-reuse-test(OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.

--disable-fail-fast(OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test(OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: DoesNOT update GitHub check status.

--stage-list "A10-PyTorch-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: DoesNOT update GitHub check status.

--gpu-type "A30, H100_PCIe"(OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: DoesNOT update GitHub check status.

--test-backend "pytorch, cpp"(OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: DoesNOT update GitHub pipeline status.

--only-multi-gpu-test(OPTIONAL) : Only run the multi-GPU tests. Note: DoesNOT update GitHub check status.

--disable-multi-gpu-test(OPTIONAL) : Disable the multi-GPU tests. Note: DoesNOT update GitHub check status.

--add-multi-gpu-test(OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.

--post-merge(OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx"(OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".

--detailed-log(OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.

--debug(OPTIONAL) :Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in thestage-list parameter to access the appropriate container environment. Note: DoesNOT update GitHub check status.

For guidance on mapping tests to stage names, seedocs/source/reference/ci-overview.md
and thescripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request.--comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

dcaox added5 commits

September 15, 2025 19:00

support return topk logprobs in torch backend

8d1af5c

Signed-off-by: Dong Cao <docao@nvidia.com>

Merge remote-tracking branch 'remotes/docao/main' into docao/support_…

13c22b0

…topk_logprobs_torch_backendSigned-off-by: Dong Cao <docao@nvidia.com>

fix rebase bug

68ebde3

Signed-off-by: Dong Cao <docao@nvidia.com>

add ut

a88ff1e

Signed-off-by: Dong Cao <docao@nvidia.com>

rename

cac915f

Signed-off-by: Dong Cao <docao@nvidia.com>

dcaox requested review froma team ascode owners

September 16, 2025 07:05

dcaox requested review fromNaveassaf andSuperjomn

September 16, 2025 07:05

svc-trtllm-gh-bot added the Community want to contributePRs initiated from Community label

Sep 16, 2025

Copy link

Contributor

coderabbitaibot commentedSep 16, 2025•
edited
Loading

📝 Walkthrough

Walkthrough

Adds end-to-end support for top‑k token log probabilities: introduces a logprobs parameter in sampling, plumbs it through workers and request objects, computes per-step top‑k logprobs in the sampler via log_softmax, removes prior constraint (logprobs > 1), and adds a unit test validating structure and ordering.

Changes

Cohort / File(s)	Summary
LLM request struct update `tensorrt_llm/_torch/pyexecutor/llm_request.py`	Adds constructor param`num_logprobs: int = 0`; stores as`self.py_num_logprobs`. Updates construction path to receive`num_logprobs` from executor requests.
Sampler top‑k logprobs implementation `tensorrt_llm/_torch/pyexecutor/sampler.py`	Imports`torch.nn.functional as F`. Replaces host logprob buffer with per-step top‑k logprobs computed via`F.log_softmax` and`topk`. Populates`req.py_topk_logprobs_vals/indices`. Changes`sample_async` signature and control path using boolean`log_probs_host`.
Parameter plumbing (scaffolding/executor) `tensorrt_llm/scaffolding/worker.py`,`tensorrt_llm/executor/worker.py`	Passes user`logprobs` through: constructs`SamplingParams(..., logprobs=task.num_logprobs, ...)` and sets`executor_request.py_num_logprobs = request.sampling_params.logprobs`.
API validation update `tensorrt_llm/llmapi/llm.py`	Removes check that restricted`sampling_params.logprobs` to 1.
Sampling params declaration `tensorrt_llm/sampling_params.py`	Adds`logprobs` field/constructor parameter.
Tests `tests/unittest/llmapi/test_llm_pytorch.py`	Adds`test_llm_topk_logprobs` validating per-token top‑k logprobs length, count per step, rank ordering (1..N), and non‑increasing logprob values by rank.

Sequence Diagram(s)

sequenceDiagram  autonumber  participant Client  participant LLMAPI as LLM API  participant Scaff as Scaffolding Worker  participant Exec as Executor Worker  participant Req as LlmRequest  participant Sampler  Client->>LLMAPI: generate(prompt, SamplingParams{logprobs=N})  LLMAPI-->>LLMAPI: validate args (no N==1 restriction)  LLMAPI->>Scaff: task params  Scaff-->>Scaff: build SamplingParams(..., logprobs=N)  Scaff->>Exec: enqueue with SamplingParams  Exec-->>Exec: set py_num_logprobs = SamplingParams.logprobs  Exec->>Req: construct LlmRequest(..., num_logprobs=N)  loop decode steps    Sampler->>Sampler: log_softmax(raw_logits)    alt logprobs requested      Sampler-->>Sampler: topk per step (vals, indices)      Sampler-->>Req: store py_topk_logprobs_vals/indices    end  end  Sampler-->>Client: outputs with per-token top‑k logprobs

Estimated code review effort

🎯 4 (Complex) | ⏱️ ~60 minutes

✨ Finishing touches

📝 Generate Docstrings

🧪 Generate unit tests

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

Tip

👮 Agentic pre-merge checks are now available in preview!

Pro plan users can now enable pre-merge checks in their settings to enforce checklists before merging PRs.

Built-in checks – Quickly apply ready-made checks to enforce title conventions, require pull request descriptions that follow templates, validate linked issues for compliance, and more.
Custom agentic checks – Define your own rules using CodeRabbit’s advanced agentic capabilities to enforce organization-specific policies and workflows. For example, you can instruct CodeRabbit’s agent to verify that API documentation is updated whenever API schema files are modified in a PR. Note: Upto 5 custom checks are currently allowed during the preview period. Pricing for this feature will be announced in a few weeks.

Please see thedocumentation for more information.

Example:

reviews:pre_merge_checks:custom_checks:      -name:"Undocumented Breaking Changes"mode:"warning"instructions:|          Pass/fail criteria: All breaking changes to public APIs, CLI flags, environment variables, configuration keys, database schemas, or HTTP/GraphQL endpoints must be documented in the "Breaking Change" section of the PR description and in CHANGELOG.md. Exclude purely internal or private changes (e.g., code not exported from package entry points or explicitly marked as internal).

Please share your feedback with us on thisDiscord post.

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.}

Pre-merge checks

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 7.69% which is insufficient. The required threshold is 80.00%.	You can run`@coderabbitai generate docstrings` to improve docstring coverage.
Description Check	⚠️ Warning	The author-provided PR body is essentially the repository template with no concrete Description or Test Coverage content filled in, so it does not explain what was changed, why, or how to validate it. Although PR metadata indicates the feature (return top-k logprobs in the PyTorch backend), the body omits implementation details, affected files, compatibility notes, and explicit test instructions needed for review. The PR Checklist is present but not clearly confirmed with CI/test evidence or documentation updates. Because the required template sections are empty or only contain boilerplate, the description is insufficient for review.	Please update the PR description by providing a concrete title following the repo template, a clear Description that lists the key code changes (files and API changes such as the new num_logprobs parameter and top-k logprob behavior), rationale and any compatibility/migration notes, and a Test Coverage section that names the new or modified tests (for example tests/unittest/llmapi/test_llm_pytorch.py::test_llm_topk_logprobs) plus instructions to reproduce. Also confirm the PR Checklist items (coding guidelines, CI stages to run, documentation updates) and link any related issue or JIRA ticket.

✅ Passed checks (1 passed)

Check name	Status	Explanation
Title Check	✅ Passed	The title "[None][feat] Return topk logprobs in torch backend" is concise, follows the repo's bracketed ticket/type convention, and accurately summarizes the main change (adding top‑k logprob support in the PyTorch backend) as reflected by edits to llm_request.py, sampler.py, worker/scaffolding files, and tests.

coderabbitaibot reviewed

Sep 16, 2025

View reviewed changes

Copy link

Contributor

coderabbitaibot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

Actionable comments posted: 6

🧹 Nitpick comments (7)

tensorrt_llm/executor/worker.py (1)
1-1:Missing NVIDIA Apache-2.0 header (2025).
Add the required copyright/license header per repo convention.
tests/unittest/llmapi/test_llm_pytorch.py (1)
1-1:Missing NVIDIA Apache-2.0 header (2025).
Add the required copyright/license header per repo convention.
tensorrt_llm/_torch/pyexecutor/llm_request.py (1)
1-1:Missing NVIDIA Apache-2.0 header (2025).
Add the required copyright/license header per repo convention.
tensorrt_llm/scaffolding/worker.py (2)
184-186:Minor: coerce task.num_logprobs to int for SamplingParams
Protect against float/str inputs from upstream task sources.
Apply this diff:
-            return_context_logits=task.return_context_logits,-            logprobs=task.num_logprobs)+            return_context_logits=task.return_context_logits,+            logprobs=(int(task.num_logprobs) if task.num_logprobs is not None else None))
1-1:Missing NVIDIA Apache-2.0 header (2025).
Add the required copyright/license header per repo convention.
tensorrt_llm/_torch/pyexecutor/sampler.py (2)
590-594:Type: log_probs_host is a boolean now
Fix the signature/type to avoid confusion and accidental tensor operations.
Apply this diff:
-    def log_probs_host(self, scheduled_requests: ScheduledRequests):+    def log_probs_host(self, scheduled_requests: ScheduledRequests) -> bool:
And in_process_requests:
-                          log_probs_host: torch.Tensor | None = None):+                          log_probs_host: bool = False):
1-1:Missing NVIDIA Apache-2.0 header (2025).
Add the required copyright/license header per repo convention.

📜 Review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and betweenb278d06 andfb6f39f.

📒 Files selected for processing (6)

tensorrt_llm/_torch/pyexecutor/llm_request.py (3 hunks)
tensorrt_llm/_torch/pyexecutor/sampler.py (7 hunks)
tensorrt_llm/executor/worker.py (1 hunks)
tensorrt_llm/llmapi/llm.py (0 hunks)
tensorrt_llm/scaffolding/worker.py (1 hunks)
tests/unittest/llmapi/test_llm_pytorch.py (1 hunks)

💤 Files with no reviewable changes (1)

tensorrt_llm/llmapi/llm.py

🧰 Additional context used

📓 Path-based instructions (3)

**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Use only spaces, no tabs; indent with 4 spaces.

Files:

tensorrt_llm/executor/worker.py
tests/unittest/llmapi/test_llm_pytorch.py
tensorrt_llm/scaffolding/worker.py
tensorrt_llm/_torch/pyexecutor/llm_request.py
tensorrt_llm/_torch/pyexecutor/sampler.py

**/*.py

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

**/*.py: Python code must target Python 3.8+.
Indent Python code with 4 spaces; do not use tabs.
Maintain module namespace when importing; prefer 'from package.subpackage import foo' then 'foo.SomeClass()' instead of importing the class directly.
Python filenames should be snake_case (e.g., some_file.py).
Python classes use PascalCase names.
Functions and methods use snake_case names.
Local variables use snake_case; prefix 'k' for variables that start with a number (e.g., k_99th_percentile).
Global variables use upper SNAKE_CASE prefixed with 'G' (e.g., G_MY_GLOBAL).
Constants use upper SNAKE_CASE (e.g., MY_CONSTANT).
Avoid shadowing variables from an outer scope.
Initialize all externally visible members of a class in the constructor.
Prefer docstrings for interfaces that may be used outside a file; comments for in-function or file-local interfaces.
Use Google-style docstrings for classes and functions (Sphinx-parsable).
Document attributes and variables inline so they render under the class/function docstring.
Avoid reflection when a simpler, explicit approach suffices (e.g., avoid dict(**locals()) patterns).
In try/except, catch the most specific exceptions possible.
For duck-typing try/except, keep the try body minimal and use else for the main logic.

Files:

tensorrt_llm/executor/worker.py
tests/unittest/llmapi/test_llm_pytorch.py
tensorrt_llm/scaffolding/worker.py
tensorrt_llm/_torch/pyexecutor/llm_request.py
tensorrt_llm/_torch/pyexecutor/sampler.py

**/*.{cpp,cxx,cc,h,hpp,hh,hxx,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Prepend the NVIDIA Apache-2.0 copyright header with current year to the top of all source files (e.g., .cpp, .h, .cu, .py).

Files:

tensorrt_llm/executor/worker.py
tests/unittest/llmapi/test_llm_pytorch.py
tensorrt_llm/scaffolding/worker.py
tensorrt_llm/_torch/pyexecutor/llm_request.py
tensorrt_llm/_torch/pyexecutor/sampler.py

🧠 Learnings (1)

📚 Learning: 2025-08-28T10:25:22.370Z

Learnt from: ixlmarPR: NVIDIA/TensorRT-LLM#7294File: tensorrt_llm/_torch/pyexecutor/sampler.py:887-891Timestamp: 2025-08-28T10:25:22.370ZLearning: In tensorrt_llm/_torch/pyexecutor/sampler.py, the draft_probs and target_probs tensors have shapes [1, steps] not [steps, vocab_size] as might be expected, making the .squeeze(0) operations appropriate for removing the batch dimension of size 1.

Applied to files:

tensorrt_llm/_torch/pyexecutor/sampler.py

🧬 Code graph analysis (4)

tensorrt_llm/executor/worker.py (1)

tensorrt_llm/scaffolding/task.py (1)
logprobs (99-100)

tests/unittest/llmapi/test_llm_pytorch.py (4)

tensorrt_llm/llmapi/llm.py (1)
generate (238-316)
tensorrt_llm/sampling_params.py (1)
SamplingParams (125-486)
tensorrt_llm/scaffolding/task.py (1)
logprobs (99-100)
tensorrt_llm/executor/result.py (1)
outputs (198-213)

tensorrt_llm/scaffolding/worker.py (2)

tests/unittest/llmapi/test_llm.py (6)
task (480-487)
task (527-532)
task (1862-1871)
task (1965-1978)
task (2326-2327)
task (2417-2436)
tensorrt_llm/scaffolding/task.py (1)
logprobs (99-100)

tensorrt_llm/_torch/pyexecutor/sampler.py (2)

tensorrt_llm/executor/result.py (1)
Logprob (37-40)
tensorrt_llm/_torch/pyexecutor/scheduler.py (1)
all_requests (38-39)

tensorrt_llm/_torch/pyexecutor/llm_request.pyShow resolvedHide resolved

tensorrt_llm/_torch/pyexecutor/sampler.pyShow resolvedHide resolved

tensorrt_llm/_torch/pyexecutor/sampler.py OutdatedShow resolvedHide resolved

tensorrt_llm/executor/worker.py OutdatedShow resolvedHide resolved

tests/unittest/llmapi/test_llm_pytorch.pyShow resolvedHide resolved

Copy link

Collaborator

WeiHaocheng commentedSep 16, 2025

/bot run

Copy link

Collaborator

tensorrt-cicd commentedSep 16, 2025

PR_Github #18737 [ run ] triggered by Bot

Copy link

Collaborator

tensorrt-cicd commentedSep 16, 2025

PR_Github #18737 [ run ] completed with stateSUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #14049 completed with status: 'FAILURE'

WeiHaocheng self-requested a review

September 17, 2025 03:01

WeiHaocheng force-pushed thedocao/support_topk_logprobs_torch_backend branch fromfb6f39f to2aaf2a7Compare

September 17, 2025 03:14

Copy link

Collaborator

WeiHaocheng commentedSep 17, 2025

/bot run

WeiHaocheng approved these changes

Sep 17, 2025

View reviewed changes

Copy link

Collaborator

tensorrt-cicd commentedSep 17, 2025

PR_Github #18876 [ run ] triggered by Bot

Copy link

Collaborator

tensorrt-cicd commentedSep 17, 2025

PR_Github #18876 [ run ] completed with stateSUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #14149 completed with status: 'FAILURE'

WeiHaocheng assigneddcaox

Sep 17, 2025

WeiHaocheng removed the Community want to contributePRs initiated from Community label

Sep 17, 2025

dcaox added4 commits

September 17, 2025 15:15

support return topk logprobs in torch backend

398cfbe

Signed-off-by: Dong Cao <docao@nvidia.com>

fix rebase bug

1ccc909

Signed-off-by: Dong Cao <docao@nvidia.com>

add ut

e79a492

Signed-off-by: Dong Cao <docao@nvidia.com>

rename

e01e84d

Signed-off-by: Dong Cao <docao@nvidia.com>

WeiHaocheng force-pushed thedocao/support_topk_logprobs_torch_backend branch frome3d28ab toe01e84dCompare

September 17, 2025 07:15

Copy link

Collaborator

WeiHaocheng commentedSep 17, 2025

/bot run

Copy link

Collaborator

tensorrt-cicd commentedSep 17, 2025

PR_Github #18924 [ run ] triggered by Bot

dcaox requested review froma team ascode owners

September 22, 2025 07:34

dcaox requested review fromShixiaowei02,brb-nv,dongjiyingdjy,galagam,mikeiovine,nv-guomingz andnv-yilinf

September 22, 2025 07:34

dcaox force-pushed thedocao/support_topk_logprobs_torch_backend branch fromb872425 to95d23f4Compare

September 22, 2025 07:36

Merge remote-tracking branch 'origin/main' into docao/support_topk_lo…

b5b89a4

…gprobs_torch_backendSigned-off-by: Dong Cao <docao@nvidia.com>

Copy link

CollaboratorAuthor

dcaox commentedSep 22, 2025

/bot run --disable-fail-fast

1 similar comment

Copy link

Collaborator

WeiHaocheng commentedSep 22, 2025

/bot run --disable-fail-fast

Copy link

Collaborator

tensorrt-cicd commentedSep 22, 2025

PR_Github #19573 [ run ] triggered by Bot

Copy link

CollaboratorAuthor

dcaox commentedSep 23, 2025

/bot run --disable-fail-fast

Copy link

Collaborator

tensorrt-cicd commentedSep 23, 2025

PR_Github #19634 [ run ] triggered by Bot

Copy link

Collaborator

tensorrt-cicd commentedSep 23, 2025

PR_Github #19573 [ run ] completed with stateABORTED
LLM/main/L0_MergeRequest_PR #14720 (Blue Ocean) completed with status: ABORTED

Copy link

Collaborator

tensorrt-cicd commentedSep 23, 2025

PR_Github #19634 [ run ] completed with stateSUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #14769 completed with status: 'SUCCESS'

dcaoxand others added3 commits

September 23, 2025 20:45

Merge remote-tracking branch 'origin/main' into docao/support_topk_lo…

5d87b82

…gprobs_torch_backendSigned-off-by: Dong Cao <docao@nvidia.com>

Merge remote-tracking branch 'origin/main' into docao/support_topk_lo…

1399857

…gprobs_torch_backendSigned-off-by: Dong Cao <docao@nvidia.com>

Merge branch 'main' into docao/support_topk_logprobs_torch_backend

e6ef004

Copy link

CollaboratorAuthor

dcaox commentedSep 24, 2025

/bot reuse-pipeline

Copy link

Collaborator

tensorrt-cicd commentedSep 24, 2025

PR_Github #19753 [ reuse-pipeline ] triggered by Bot

Copy link

Collaborator

tensorrt-cicd commentedSep 24, 2025

PR_Github #19753 [ reuse-pipeline ] completed with stateSUCCESS
ReusingPR_Github #19634 for commite6ef004

WeiHaocheng merged commit2f8dc6f intoNVIDIA:main

Sep 24, 2025

5 checks passed

Tabrizian added a commit to Tabrizian/TensorRT-LLM that referenced this pull request

Sep 24, 2025

Revert "[None][feat] Return topk logprobs in torch backend (NVIDIA#7756…

0a80d56

…)"This reverts commit2f8dc6f.Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

brb-nv pushed a commit that referenced this pull request

Sep 24, 2025

[None][fix] Revert "[None][feat] Return topk logprobs in torch backend (

da30d49

#7756)" (#7969)Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com>

coderabbitaibot mentioned this pull request

Sep 25, 2025

[None][feat] Return topk logprobs in torch backend#7976

Merged

1 task

Reviewers

coderabbitai[bot]coderabbitai[bot] left review comments

SuperjomnSuperjomn approved these changes

WeiHaochengWeiHaocheng approved these changes

QiJuneQiJune approved these changes

NaveassafAwaiting requested review from NaveassafNaveassaf is a code owner automatically assigned from NVIDIA/trt-llm-torch-runtime-devs

dongjiyingdjyAwaiting requested review from dongjiyingdjydongjiyingdjy was automatically assigned from NVIDIA/trt-llm-torch-models-qwen-devs

brb-nvAwaiting requested review from brb-nvbrb-nv was automatically assigned from NVIDIA/trt-llm-torch-models-devs

nv-yilinfAwaiting requested review from nv-yilinfnv-yilinf was automatically assigned from NVIDIA/trt-llm-torch-spec-decoding

galagamAwaiting requested review from galagamgalagam was automatically assigned from NVIDIA/trt-llm-torch-autodeploy-devs

Shixiaowei02Awaiting requested review from Shixiaowei02Shixiaowei02 was automatically assigned from NVIDIA/trt-llm-doc-owners

nv-guomingzAwaiting requested review from nv-guomingznv-guomingz was automatically assigned from NVIDIA/trt-llm-doc-owners

mikeiovineAwaiting requested review from mikeiovinemikeiovine was automatically assigned from NVIDIA/trt-llm-torch-modules

Labels

None yet

6 participants

Movatterモバイル変換

[None][feat] Return topk logprobs in torch backend#7756

[None][feat] Return topk logprobs in torch backend#7756

Uh oh!

Conversation

dcaox commentedSep 16, 2025• editedLoading Uh oh!There was an error while loading.Please reload this page.

Uh oh!

Summary by CodeRabbit

Description

Test Coverage

PR Checklist

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

coderabbitaibot commentedSep 16, 2025• editedLoading Uh oh!There was an error while loading.Please reload this page.

Uh oh!

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Pre-merge checks

Uh oh!

coderabbitaibot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

WeiHaocheng commentedSep 16, 2025

Uh oh!

tensorrt-cicd commentedSep 16, 2025

Uh oh!

tensorrt-cicd commentedSep 16, 2025

Uh oh!

WeiHaocheng commentedSep 17, 2025

Uh oh!

tensorrt-cicd commentedSep 17, 2025

Uh oh!

tensorrt-cicd commentedSep 17, 2025

Uh oh!

WeiHaocheng commentedSep 17, 2025

Uh oh!

tensorrt-cicd commentedSep 17, 2025

Uh oh!

dcaox commentedSep 22, 2025

Uh oh!

WeiHaocheng commentedSep 22, 2025

Uh oh!

tensorrt-cicd commentedSep 22, 2025

Uh oh!

dcaox commentedSep 23, 2025

Uh oh!

tensorrt-cicd commentedSep 23, 2025

Uh oh!

tensorrt-cicd commentedSep 23, 2025

Uh oh!

tensorrt-cicd commentedSep 23, 2025

Uh oh!

dcaox commentedSep 24, 2025

Uh oh!

tensorrt-cicd commentedSep 24, 2025

Uh oh!

tensorrt-cicd commentedSep 24, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

6 participants

dcaox commentedSep 16, 2025•
edited
Loading

coderabbitaibot commentedSep 16, 2025•
edited
Loading