[None][doc] add blackwell information into support matrix #6740

nv-guomingz · 2025-08-08T06:44:09Z

Add Blackwell information into support matrix.

Summary by CodeRabbit

Documentation
- Updated the support matrix to include Blackwell GPU architecture with details on supported precisions (FP32, FP16, BF16, FP8, FP4, INT8, INT4).
- Added a new "FP4 Support" section highlighting NVIDIA B200 GPU compatibility and optimized FP4 kernel usage for efficient low-precision inference.

coderabbitai · 2025-08-08T06:44:16Z

📝 Walkthrough

Walkthrough

The support matrix documentation for TensorRT-LLM was updated to list the Blackwell GPU architecture, detailing its supported numerical precisions (FP32, FP16, BF16, FP8, FP4, INT8, INT4). Additionally, a new "FP4 Support" subsection was added to the overview documentation, introducing FP4 format support for NVIDIA B200 GPUs. No other changes were made to compatibility or precision support for other architectures.

Changes

Cohort / File(s)	Change Summary
Support Matrix Documentation `docs/source/reference/support-matrix.md`	Added Blackwell (SM100/SM120) GPU architecture and its supported precisions to the support matrix.
Overview Documentation Update `docs/source/overview.md`	Added a new "FP4 Support" subsection explaining FP4 precision support for NVIDIA B200 GPUs.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

[Fix][Chore][Qwen3] fix bug of using fp4 on sm120 #6065: Fixes a bug disabling NVFP4 output support on SM120, directly related to FP4 support on Blackwell GPUs.

Suggested labels

Documentation

Suggested reviewers

litaotju
schetlur-nv

📜 Recent review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between f20873f and 5338811.

📒 Files selected for processing (2)

docs/source/overview.md (1 hunks)
docs/source/reference/support-matrix.md (1 hunks)

✅ Files skipped from review due to trivial changes (1)

docs/source/overview.md

🚧 Files skipped from review as they are similar to previous changes (1)

docs/source/reference/support-matrix.md

✨ Finishing Touches

🧪 Generate unit tests

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

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

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

Review comments: Directly reply to a review comment made by CodeRabbit. Example:
- I pushed a fix in commit <commit_id>, please review it.
- Explain this complex logic.
- Open a follow-up GitHub issue for this discussion.
Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
- @coderabbitai explain this code block.
PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
- @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
- @coderabbitai read src/utils.ts and explain its main purpose.
- @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

CodeRabbit Commands (Invoked using PR comments)

@coderabbitai pause to pause the reviews on a PR.
@coderabbitai resume to resume the paused reviews.
@coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
@coderabbitai full review to do a full review from scratch and review all the files again.
@coderabbitai summary to regenerate the summary of the PR.
@coderabbitai generate docstrings to generate docstrings for this PR.
@coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
@coderabbitai generate unit tests to generate unit tests for this PR.
@coderabbitai resolve resolve all the CodeRabbit review comments.
@coderabbitai configuration to show the current CodeRabbit configuration for the repository.
@coderabbitai help to get help.

Other keywords and placeholders

Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
Add @coderabbitai or @coderabbitai title anywhere in the PR title to generate the title automatically.

Documentation and Community

Visit our Documentation for detailed information on how to use CodeRabbit.
Join our Discord Community to get help, request features, and share feedback.
Follow us on X/Twitter for updates and announcements.

nv-guomingz · 2025-08-08T06:44:53Z

/bot skip --comment "docs change only"

coderabbitai

Actionable comments posted: 1

🧹 Nitpick comments (1)

docs/source/reference/support-matrix.md (1)
161-165: Add FP4 scope footnote to set expectations.

FP4 is new with Blackwell; model/operator coverage in TensorRT-LLM is evolving. Consider adding a footnote to avoid over-promising.

Inline marker change:
-    - Blackwell (SM100/SM120) - FP32, FP16, BF16, FP8, FP4, INT8, INT4
+    - Blackwell (SM100/SM120) - FP32, FP16, BF16, FP8, FP4[^fp4], INT8, INT4
Then append a new footnote in the existing footnotes block (near other [^…] notes):
[^fp4]: FP4 support is available on Blackwell GPUs and is not implemented for all models/ops yet. Refer to {ref}`precision` and examples for up-to-date coverage.

📜 Review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 28b762a and f20873f.

📒 Files selected for processing (1)

docs/source/reference/support-matrix.md (1 hunks)

🧰 Additional context used

🧠 Learnings (6)

📓 Common learnings

Learnt from: yibinl-nvidia
PR: NVIDIA/TensorRT-LLM#6506
File: examples/models/core/mixtral/requirements.txt:3-3
Timestamp: 2025-08-01T15:14:45.673Z
Learning: In TensorRT-LLM, examples directory can have different dependency versions than the root requirements.txt file. Version conflicts between root and examples dependencies are acceptable because examples are designed to be standalone and self-contained.

Learnt from: galagam
PR: NVIDIA/TensorRT-LLM#6487
File: tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py:1-12
Timestamp: 2025-08-06T13:58:07.506Z
Learning: In TensorRT-LLM, test files (files under tests/ directories) do not require NVIDIA copyright headers, unlike production source code files. Test files typically start directly with imports, docstrings, or code.

Learnt from: moraxu
PR: NVIDIA/TensorRT-LLM#6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.

Learnt from: venkywonka
PR: NVIDIA/TensorRT-LLM#6650
File: tests/integration/test_lists/qa/llm_perf_cluster.yml:33-37
Timestamp: 2025-08-06T03:47:16.802Z
Learning: Ministral is a valid and distinct model family from Mistral AI, separate from their regular Mistral models. Ministral 8B is specifically designed for edge computing and on-device applications, released in October 2024. In TensorRT-LLM test configurations, "ministral_8b" and "ministral_8b_fp8" are correct model identifiers and should not be changed to "mistral_8b".

Learnt from: venkywonka
PR: NVIDIA/TensorRT-LLM#6650
File: tests/integration/test_lists/qa/llm_perf_cluster.yml:33-37
Timestamp: 2025-08-06T03:47:16.802Z
Learning: Ministral is a valid model name from Mistral AI, distinct from the regular Mistral models. In TensorRT-LLM test configurations, "ministral_8b" and "ministral_8b_fp8" are correct model identifiers and should not be changed to "mistral_8b".

📚 Learning: 2025-08-06T13:58:07.506Z

Learnt from: galagam
PR: NVIDIA/TensorRT-LLM#6487
File: tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py:1-12
Timestamp: 2025-08-06T13:58:07.506Z
Learning: In TensorRT-LLM, test files (files under tests/ directories) do not require NVIDIA copyright headers, unlike production source code files. Test files typically start directly with imports, docstrings, or code.

Applied to files:

docs/source/reference/support-matrix.md

📚 Learning: 2025-08-06T21:22:55.018Z

Learnt from: CR
PR: NVIDIA/TensorRT-LLM#0
File: CODING_GUIDELINES.md:0-0
Timestamp: 2025-08-06T21:22:55.018Z
Learning: Applies to **/*.{cpp,h,hpp,cc,cxx,cu,py} : All TensorRT-LLM Open Source Software code should contain an NVIDIA copyright header that includes the current year. This includes .cpp, .h, .cu, .py, and any other source files which are compiled or interpreted.

Applied to files:

docs/source/reference/support-matrix.md

📚 Learning: 2025-08-01T15:14:45.673Z

Learnt from: yibinl-nvidia
PR: NVIDIA/TensorRT-LLM#6506
File: examples/models/core/mixtral/requirements.txt:3-3
Timestamp: 2025-08-01T15:14:45.673Z
Learning: In TensorRT-LLM, examples directory can have different dependency versions than the root requirements.txt file. Version conflicts between root and examples dependencies are acceptable because examples are designed to be standalone and self-contained.

Applied to files:

docs/source/reference/support-matrix.md

📚 Learning: 2025-08-06T03:47:16.802Z

Learnt from: venkywonka
PR: NVIDIA/TensorRT-LLM#6650
File: tests/integration/test_lists/qa/llm_perf_cluster.yml:33-37
Timestamp: 2025-08-06T03:47:16.802Z
Learning: Ministral is a valid and distinct model family from Mistral AI, separate from their regular Mistral models. Ministral 8B is specifically designed for edge computing and on-device applications, released in October 2024. In TensorRT-LLM test configurations, "ministral_8b" and "ministral_8b_fp8" are correct model identifiers and should not be changed to "mistral_8b".

Applied to files:

docs/source/reference/support-matrix.md

📚 Learning: 2025-08-06T03:47:16.802Z

Learnt from: venkywonka
PR: NVIDIA/TensorRT-LLM#6650
File: tests/integration/test_lists/qa/llm_perf_cluster.yml:33-37
Timestamp: 2025-08-06T03:47:16.802Z
Learning: Ministral is a valid model name from Mistral AI, distinct from the regular Mistral models. In TensorRT-LLM test configurations, "ministral_8b" and "ministral_8b_fp8" are correct model identifiers and should not be changed to "mistral_8b".

Applied to files:

docs/source/reference/support-matrix.md

⏰ 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: Pre-commit Check

docs/source/reference/support-matrix.md

tensorrt-cicd · 2025-08-08T06:49:57Z

PR_Github #14582 [ skip ] triggered by Bot

tensorrt-cicd · 2025-08-08T07:03:52Z

PR_Github #14582 [ skip ] completed with state SUCCESS
Skipping testing for commit f20873f

docs/source/overview.md

nv-guomingz · 2025-08-29T16:00:12Z

/bot skip --comment "docs only"

tensorrt-cicd · 2025-08-29T16:08:25Z

PR_Github #17005 [ skip ] triggered by Bot

tensorrt-cicd · 2025-08-29T16:27:21Z

PR_Github #17005 [ skip ] completed with state SUCCESS
Skipping testing for commit 9b062a8

Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>

nv-guomingz · 2025-09-01T17:46:47Z

/bot skip --comment "docs only change"

tensorrt-cicd · 2025-09-01T17:51:50Z

PR_Github #17245 [ skip ] triggered by Bot

tensorrt-cicd · 2025-09-01T18:04:43Z

PR_Github #17245 [ skip ] completed with state SUCCESS
Skipping testing for commit dda2681

Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>

Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>

nv-guomingz requested a review from Tracin August 8, 2025 06:44

nv-guomingz requested a review from a team as a code owner August 8, 2025 06:44

nv-guomingz requested review from chzblych and kaiyux August 8, 2025 06:44

nv-guomingz added the 1.0_doc label Aug 8, 2025

nv-guomingz requested review from juney-nvidia and laikhtewari August 8, 2025 06:45

Tracin approved these changes Aug 8, 2025

View reviewed changes

coderabbitai bot reviewed Aug 8, 2025

View reviewed changes

docs/source/reference/support-matrix.md Show resolved Hide resolved

nv-guomingz force-pushed the user/guomingz/add-blackwell-info branch from f20873f to 5338811 Compare August 8, 2025 06:55

juney-nvidia reviewed Aug 8, 2025

View reviewed changes

docs/source/overview.md Show resolved Hide resolved

laikhtewari approved these changes Aug 29, 2025

View reviewed changes

docs/source/overview.md Show resolved Hide resolved

nv-guomingz force-pushed the user/guomingz/add-blackwell-info branch from 5338811 to 9b062a8 Compare August 29, 2025 15:48

nv-guomingz requested a review from a team as a code owner August 29, 2025 15:48

[None][doc] add blackwell supporting into doc.

dda2681

Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>

nv-guomingz force-pushed the user/guomingz/add-blackwell-info branch from 9b062a8 to dda2681 Compare September 1, 2025 15:45

MartinMarciniszyn approved these changes Sep 1, 2025

View reviewed changes

nv-guomingz enabled auto-merge (squash) September 1, 2025 17:46

nv-guomingz merged commit 95e0318 into NVIDIA:release/1.0 Sep 1, 2025
4 checks passed

dominicshanshan pushed a commit to dominicshanshan/TensorRT-LLM that referenced this pull request Sep 9, 2025

[None][doc] add blackwell information into support matrix (NVIDIA#6740)

8779bf1

Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>

nv-guomingz deleted the user/guomingz/add-blackwell-info branch September 30, 2025 08:04

[None][doc] add blackwell information into support matrix #6740

[None][doc] add blackwell information into support matrix #6740

Uh oh!

Conversation

nv-guomingz commented Aug 8, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Uh oh!

coderabbitai bot commented Aug 8, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Suggested labels

Suggested reviewers

Chat

Support

CodeRabbit Commands (Invoked using PR comments)

Other keywords and placeholders

Documentation and Community

Uh oh!

nv-guomingz commented Aug 8, 2025

Uh oh!

coderabbitai bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

tensorrt-cicd commented Aug 8, 2025

Uh oh!

tensorrt-cicd commented Aug 8, 2025

Uh oh!

Uh oh!

Uh oh!

nv-guomingz commented Aug 29, 2025

Uh oh!

tensorrt-cicd commented Aug 29, 2025

Uh oh!

tensorrt-cicd commented Aug 29, 2025

Uh oh!

nv-guomingz commented Sep 1, 2025

Uh oh!

tensorrt-cicd commented Sep 1, 2025

Uh oh!

tensorrt-cicd commented Sep 1, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

6 participants

nv-guomingz commented Aug 8, 2025 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Aug 8, 2025 •

edited

Loading