[None][doc]: remove the outdated features which marked as Experimental (#5995) #6681
Conversation
📝 WalkthroughWalkthroughThis change updates documentation across multiple files to revise feature status terminology, primarily replacing "experimental" with "prototype" or "beta" in various feature descriptions, notes, and section headers. Some explanatory notes about experimental status were removed or reworded, but no technical content, logic, or functionality was changed. Changes
Sequence Diagram(s)No sequence diagram generated, as all changes are limited to documentation and do not affect control flow or feature logic. Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
Suggested labels
Suggested reviewers
Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. ✨ Finishing Touches🧪 Generate unit tests
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (6)
docs/source/architecture/model-weights-loader.md (1)
252-253: Clarify wording of default-enablement sentence“The weights loader is enabled for LLaMA family models and Qwen models by default with TensorRT flow only.” is hard to parse. Consider:
-The weights loader is enabled for LLaMA family models and Qwen models by default with TensorRT flow only. +The weights loader is enabled by default for LLaMA-family and Qwen models **when the TensorRT flow is used**.docs/source/advanced/speculative-decoding.md (1)
171-172: Grammar & spacing fixDrop the redundant “of” and insert a missing space after “engine”.
-... performed inside of the TensorRT engine(EAGLE-1 and EAGLE-2 are both supported). +... performed inside the TensorRT engine (EAGLE-1 and EAGLE-2 are both supported).examples/models/core/llama/README.md (2)
679-681: Capitalize and tighten FP8 GEMV noteMinor style improvement for readability.
-Note: use FP8 GEMV to optimize performance in FP8 small-batch-size cases. +Note: Use the FP8 GEMV plugin to optimize small-batch-size FP8 workloads.
697-699: Consistent kernel naming and punctuation
gemv/gemmmixes lower- and upper-case; stick to upper-case for acronyms and add a comma after “engine”.-**Note**: FP8 gemv plugin uses CUDA cores to compute, by contrast to Tensor Core gemm kernel within cuBLAS. +**Note**: The FP8 GEMV plugin uses CUDA cores, in contrast to the Tensor-Core GEMM kernels within cuBLAS.examples/models/core/deepseek_v3/README.md (2)
33-33: Capitalize product name for consistencyIn the bullet text, “triton inference server” should follow the official branding “Triton Inference Server” (capital “T” and “I”). This capitalization is already used elsewhere in project docs and improves professionalism.
- - [tensorrtllm\_backend for triton inference server (Prototype)](#tensorrtllm_backend-for-triton-inference-server-prototype) + - [tensorrtllm\_backend for Triton Inference Server (Prototype)](#tensorrtllm_backend-for-triton-inference-server-prototype)
395-397: Minor wording & branding polish
- Heading: same capitalization concern as above – “Triton Inference Server” is the proper name.
- Body: “the pytorch path” → “the PyTorch path/back-end” to keep style consistent and capitalize the framework name.
-### tensorrtllm_backend for triton inference server (Prototype) +### tensorrtllm_backend for Triton Inference Server (Prototype) -To serve the model using [tensorrtllm_backend](https://github.com/triton-inference-server/tensorrtllm_backend.git), make sure the version is v0.19+ in which the pytorch path is added as a prototype feature. +To serve the model using [tensorrtllm_backend](https://github.com/triton-inference-server/tensorrtllm_backend.git), ensure you are on version v0.19 or later, where the **PyTorch** path is available as a prototype feature.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (14)
README.md(1 hunks)docs/source/advanced/disaggregated-service.md(1 hunks)docs/source/advanced/gpt-attention.md(0 hunks)docs/source/advanced/speculative-decoding.md(1 hunks)docs/source/architecture/model-weights-loader.md(1 hunks)docs/source/performance/perf-benchmarking.md(0 hunks)docs/source/reference/precision.md(1 hunks)docs/source/torch.md(1 hunks)examples/auto_deploy/README.md(2 hunks)examples/disaggregated/README.md(1 hunks)examples/eagle/README.md(0 hunks)examples/models/core/deepseek_v3/README.md(2 hunks)examples/models/core/llama/README.md(2 hunks)examples/sample_weight_stripping/README.md(2 hunks)
💤 Files with no reviewable changes (3)
- examples/eagle/README.md
- docs/source/advanced/gpt-attention.md
- docs/source/performance/perf-benchmarking.md
🧰 Additional context used
🧠 Learnings (7)
📚 Learning: in tensorrt-llm testing, it's common to have both cli flow tests (test_cli_flow.py) and pytorch api ...
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.
Applied to files:
examples/sample_weight_stripping/README.mddocs/source/advanced/speculative-decoding.mddocs/source/torch.mdREADME.mddocs/source/architecture/model-weights-loader.mdexamples/models/core/deepseek_v3/README.md
📚 Learning: in tensorrt-llm, test files (files under tests/ directories) do not require nvidia copyright headers...
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:
examples/sample_weight_stripping/README.mddocs/source/torch.mdREADME.mddocs/source/architecture/model-weights-loader.mdexamples/models/core/deepseek_v3/README.md
📚 Learning: in tensorrt-llm, examples directory can have different dependency versions than the root requirement...
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:
examples/sample_weight_stripping/README.mddocs/source/advanced/speculative-decoding.mddocs/source/torch.mdREADME.mddocs/source/architecture/model-weights-loader.mdexamples/models/core/deepseek_v3/README.md
📚 Learning: in tensorrt-llm's multimodal processing pipeline, shared tensor recovery using `from_shared_tensor()...
Learnt from: yechank-nvidia
PR: NVIDIA/TensorRT-LLM#6254
File: tensorrt_llm/_torch/pyexecutor/model_engine.py:1201-1204
Timestamp: 2025-07-22T09:22:14.726Z
Learning: In TensorRT-LLM's multimodal processing pipeline, shared tensor recovery using `from_shared_tensor()` is only needed during the context phase. Generation requests reuse the already-recovered tensor data and only need to call `strip_for_generation()` to remove unnecessary multimodal data while preserving the recovered tensors. This avoids redundant tensor recovery operations during generation.
Applied to files:
examples/sample_weight_stripping/README.mddocs/source/advanced/speculative-decoding.mdREADME.mddocs/source/architecture/model-weights-loader.md
📚 Learning: in tensorrt_llm/executor/worker.py, the lora adapter cache optimization logic that checks `is_adapte...
Learnt from: amitz-nv
PR: NVIDIA/TensorRT-LLM#5616
File: tensorrt_llm/executor/worker.py:375-384
Timestamp: 2025-07-17T09:01:27.402Z
Learning: In tensorrt_llm/executor/worker.py, the LoRA adapter cache optimization logic that checks `is_adapter_in_cpu_cache()` and conditionally passes None for weights/config has a known race condition issue that cannot be solved with simple error handling or verification checks. This is a known limitation that requires a more comprehensive solution.
Applied to files:
docs/source/architecture/model-weights-loader.md
📚 Learning: ministral is a valid model name from mistral ai, distinct from the regular mistral models. in tensor...
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:
examples/models/core/deepseek_v3/README.md
📚 Learning: ministral is a valid and distinct model family from mistral ai, separate from their regular mistral ...
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:
examples/models/core/deepseek_v3/README.md
🪛 LanguageTool
docs/source/advanced/speculative-decoding.md
[style] ~171-~171: This phrase is redundant. Consider using “inside”.
Context: ...nd draft token generation are performed inside of the TensorRT engine(EAGLE-1 and EAGLE-2...
(OUTSIDE_OF)
🔇 Additional comments (11)
docs/source/reference/precision.md (1)
104-107: GPT-J example link path verifiedThe directory
examples/models/contrib/gptj/exists in the repository, so thesource:examples/models/contrib/gptjlink will resolve correctly.examples/disaggregated/README.md (1)
86-88: Update internal anchor references after header renameRenaming the header to “Dynamic scaling (Prototype)” changes its markdown anchor (now
#dynamic-scaling-prototype).
Please make sure any intra-document links or external references to the old#dynamic-scalinganchor are updated accordingly.README.md (1)
253-253: LGTM! Terminology update aligns with project-wide standardization.The change from "experimental" to "prototype" for the AutoDeploy backend description is consistent with the broader documentation update effort across the project.
docs/source/advanced/disaggregated-service.md (2)
3-3: LGTM! Header terminology update is consistent.The section header change from "Experimental" to "Prototype" aligns with the project-wide effort to standardize feature status descriptions.
7-7: LGTM! Note text updated consistently.The note text properly reflects the new "prototype" status, maintaining consistency with the header change and the broader documentation update.
examples/sample_weight_stripping/README.md (2)
15-15: LGTM! Table of contents updated consistently.The table of contents entry correctly reflects the section header change from "Experimental" to "Prototype".
242-242: LGTM! Section header terminology standardized.The section header change from "Experimental" to "Prototype" is consistent with the project-wide documentation update and aligns with the table of contents change.
examples/auto_deploy/README.md (2)
9-9: LGTM! Feature description updated consistently.The change from "experimental" to "prototype" in the AutoDeploy feature description aligns with the project-wide terminology standardization effort.
453-453: LGTM! Disclaimer updated with consistent terminology.The disclaimer section properly reflects the new "prototype" status while maintaining the appropriate cautionary language about the feature being in active development and beta stage.
docs/source/torch.md (2)
5-5: LGTM! Feature status updated to beta.The note correctly reflects the change from "experimental" to "beta" status for the PyTorch backend feature.
7-7: LGTM! Description simplified appropriately.The removal of "experimental" qualifier from the backend description streamlines the text while maintaining clarity about it being a new backend based on PyTorch.
|
/bot run --stage-list "A10-Build-docs" |
|
PR_Github #14417 [ run ] triggered by Bot |
|
PR_Github #14417 [ run ] completed with state |
|
/bot run --stage-list "A10-Build_Docs" |
nv-guomingz
force-pushed
the
user/guomingz/cherry-pick-5995
branch
from
e2b6edb to
53f94a4
Compare
|
PR_Github #14426 [ ] completed with state |
2 participants
Cherry-pick #5995 into 1.0 release branch.
Summary by CodeRabbit