[None][fix] Add TP information in weight scale loading in WeightOnlyQuantLinearMethod #7732
Conversation
|
/bot run |
|
PR_Github #18632 [ run ] triggered by Bot |
|
PR_Github #18632 [ run ] completed with state |
stnie
force-pushed
the
develop/quantization/load_int8wo_tp
branch
from
5fcec50 to
ae57700
Compare
📝 WalkthroughWalkthroughThe call to load weight scales in the fused QKV path of WeightOnlyQuantLinearMethod was updated to pass explicit tensor-parallel parameters (tp_size, tp_rank, tp_mode), making the loading shard-aware per the module’s TP configuration. Other surrounding logic, including q/k/v concatenation and assignment to module.weight_scale, remains unchanged. Changes
Sequence Diagram(s)sequenceDiagram
participant M as Module (WeightOnlyQuantLinearMethod)
participant L as load_weight_scales
M->>L: load_weight_scales(weights, tp_size=module.tp_size, tp_rank=module.tp_rank, tp_mode=module.tp_mode)
note over L: Return TP-shard-aware weight_scales
L-->>M: weight_scales
M->>M: Assign to module.weight_scale after fused QKV processing
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ Finishing touches
🧪 Generate unit tests
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.
Please see the documentation 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 this Discord 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. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
tensorrt_llm/_torch/modules/linear.py (1)
1447-1447: Mirror the TP fix in W4A16_AWQ fused-QKV path.
W4A16_AWQ_LinearMethod.load_weights_fused_qkv_linearcallsself.load_weight_scales(weights)without TP args, likely causing incorrect scale sharding under TP>1 (same root cause you just fixed for INT8 WO).Apply:
- weight_scales = self.load_weight_scales(weights) + weight_scales = self.load_weight_scales( + weights, + tp_size=module.tp_size, + tp_rank=module.tp_rank, + tp_mode=module.tp_mode, + )
🧹 Nitpick comments (1)
tensorrt_llm/_torch/modules/linear.py (1)
1249-1274: Optional: avoid hard-coding device in load_weight_scales.
WeightOnlyQuantLinearMethod.load_weight_scalesusestorch.device("cuda"). Prefer aligning with the parameter device (e.g.,module.weight_scale.device) to prevent cross-device copies in nonstandard setups. This would require threading adevicearg through the call.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tensorrt_llm/_torch/modules/linear.py(1 hunks)
🧰 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/_torch/modules/linear.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/_torch/modules/linear.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/_torch/modules/linear.py
🧬 Code graph analysis (1)
tensorrt_llm/_torch/modules/linear.py (2)
tensorrt_llm/_torch/distributed/communicator.py (2)
tp_size(46-47)tp_rank(54-55)tensorrt_llm/mapping.py (1)
tp_rank(338-339)
⏰ 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
stnie
force-pushed
the
develop/quantization/load_int8wo_tp
branch
from
ae57700 to
80bf557
Compare
|
/bot run |
|
PR_Github #18947 [ run ] triggered by Bot |
|
PR_Github #18947 [ run ] completed with state |
stnie
force-pushed
the
develop/quantization/load_int8wo_tp
branch
from
80bf557 to
ab7e838
Compare
|
/bot run |
|
PR_Github #18969 [ run ] triggered by Bot |
|
PR_Github #18969 [ run ] completed with state |
…d to include tensor parallel parameters Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
stnie
force-pushed
the
develop/quantization/load_int8wo_tp
branch
from
ab7e838 to
cef8e6f
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #19025 [ run ] triggered by Bot |
|
PR_Github #19025 [ run ] completed with state |
…uantLinearMethod (NVIDIA#7732) Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
…uantLinearMethod (NVIDIA#7732) Signed-off-by: Stefan Niebler <82932102+stnie@users.noreply.github.com>
4 participants
Summary by CodeRabbit
Bug Fixes
Performance and Stability
Description
Using int8 weight only quanization could not load weights when using TP > 1, as loading the weight scales did not get the relevant information regarding TP size/rank/etc.
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 Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test 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.
Details
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: Does NOT update GitHub check status.--stage-list "A10-PyTorch-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT 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: Does NOT 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: Does NOT update GitHub pipeline status.--only-multi-gpu-test(OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.--disable-multi-gpu-test(OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT 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-listparameter to access the appropriate container environment. Note: Does NOT update GitHub check status.For guidance on mapping tests to stage names, see
docs/source/reference/ci-overview.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip 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-pipelineReuse 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.