[None][chore] add TorchLlmArgs to the connector api #7493
Conversation
📝 WalkthroughWalkthroughPropagates TorchLlmArgs into KV cache components. Updates constructor signatures for worker/leader/scheduler to accept llm_args (and tokens_per_block where applicable). Adjusts executor creator to pass new arguments when launching worker and scheduler. Example connector imports TorchLlmArgs and aligns with new base-class parameters. No other logic changes. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
actor User
participant Creator as PyExecutorCreator
participant Worker as KvCacheConnectorWorker
participant Scheduler as KvCacheConnectorScheduler
User->>Creator: create_executor(llm_args, tokens_per_block)
note over Creator: Prepare tasks
Creator->>Worker: start(llm_args)
activate Worker
Worker-->>Creator: ready
deactivate Worker
Creator->>Scheduler: start(llm_args, tokens_per_block)
activate Scheduler
Scheduler-->>Creator: ready
deactivate Scheduler
note over Creator,Worker: llm_args now available in components
note over Creator,Scheduler: tokens_per_block set in scheduler
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
✨ 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/Issue comments)Type Other keywords and placeholders
Status, 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: 2
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
tensorrt_llm/_torch/pyexecutor/py_executor_creator.py (1)
436-447: Validate tokens_per_block before scheduler instantiation
In tensorrt_llm/_torch/pyexecutor/py_executor_creator.py (around theexecutor.submit(scheduler_cls, …)block at lines 448–454), add a guard to ensureexecutor_config.tokens_per_blockis a positive integer and raise a clear error if not.examples/llm-api/llm_kv_cache_connector.py (1)
28-33: Python 3.8 compatibility: replace PEP 585 built-in genericsThe repo targets Python 3.8+. Annotations like list[tuple[str, int]] require 3.9+. Switch to typing.List/typing.Tuple (and add imports) to avoid SyntaxError on 3.8.
You can adjust as follows (outside the changed hunk):
from typing import List, Tuple # add near other imports @dataclass class PersistentKvCacheConnectorMetadata: load: List[Tuple[str, int]] = field(default_factory=list) save: List[Tuple[str, int]] = field(default_factory=list)
🧹 Nitpick comments (2)
tensorrt_llm/_torch/pyexecutor/kv_cache_connector.py (1)
84-86: Store llm_args on worker: OK; consider documenting intended usageAttribute is set but unused here. A brief docstring or comment clarifying expected fields (e.g., kv_connector_config) would help implementers.
examples/llm-api/llm_kv_cache_connector.py (1)
1-4: Add NVIDIA/SPDX header for consistencyOther TRT-LLM Python files include the SPDX/NVIDIA header. Mirror that here.
Example (insert at file top):
# SPDX-FileCopyrightText: Copyright (c) 2022-2025 NVIDIA CORPORATION & AFFILIATES. # SPDX-License-Identifier: Apache-2.0
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (3)
examples/llm-api/llm_kv_cache_connector.py(3 hunks)tensorrt_llm/_torch/pyexecutor/kv_cache_connector.py(3 hunks)tensorrt_llm/_torch/pyexecutor/py_executor_creator.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (4)
**/*
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Filenames compiled into a target must be case-insensitively unique
Files:
tensorrt_llm/_torch/pyexecutor/py_executor_creator.pyexamples/llm-api/llm_kv_cache_connector.pytensorrt_llm/_torch/pyexecutor/kv_cache_connector.py
**/*.{h,hpp,hh,hxx,cc,cpp,cxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Use spaces, not tabs; indent 4 spaces
Files:
tensorrt_llm/_torch/pyexecutor/py_executor_creator.pyexamples/llm-api/llm_kv_cache_connector.pytensorrt_llm/_torch/pyexecutor/kv_cache_connector.py
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Code must target Python 3.8+
Indent with 4 spaces; do not use tabs (Python)
Maintain module namespace on import: prefer from package.subpackage import foo; use foo.Symbol()
Python filenames use snake_case
Python class names use PascalCase
Python functions and methods use snake_case
Python local variables use snake_case; if starting with a number concept, prefix with k (e.g., k_99th_percentile)
Python global variables use G_ prefix with UPPER_SNAKE_CASE
Python constants use UPPER_SNAKE_CASE
Avoid shadowing variables from outer scopes
Initialize all externally visible class members in init
For public interfaces, prefer docstrings over comments; comments should be for in-function or file-local interfaces
Use Google-style docstrings for classes and functions (Sphinx-parsable)
Document attributes and variables inline with docstrings immediately after assignment
Avoid reflection when a non-reflective approach suffices
Limit except clauses to specific exceptions where possible
When using try/except for duck-typing, keep try body minimal and move logic to else
Files:
tensorrt_llm/_torch/pyexecutor/py_executor_creator.pyexamples/llm-api/llm_kv_cache_connector.pytensorrt_llm/_torch/pyexecutor/kv_cache_connector.py
**/*.{cpp,cc,cxx,h,hpp,hh,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend NVIDIA copyright header (current year) to all source files
Files:
tensorrt_llm/_torch/pyexecutor/py_executor_creator.pyexamples/llm-api/llm_kv_cache_connector.pytensorrt_llm/_torch/pyexecutor/kv_cache_connector.py
🧬 Code graph analysis (3)
tensorrt_llm/_torch/pyexecutor/py_executor_creator.py (1)
tensorrt_llm/_torch/attention_backend/trtllm.py (1)
tokens_per_block(581-585)
examples/llm-api/llm_kv_cache_connector.py (1)
tensorrt_llm/llmapi/llm_args.py (2)
KvCacheConnectorConfig(407-419)TorchLlmArgs(2173-2606)
tensorrt_llm/_torch/pyexecutor/kv_cache_connector.py (1)
tensorrt_llm/llmapi/llm_args.py (1)
TorchLlmArgs(2173-2606)
🔇 Additional comments (2)
tensorrt_llm/_torch/pyexecutor/py_executor_creator.py (1)
441-441: Passing llm_args into worker ctor looks correctMatches the updated worker interface. No concerns here.
examples/llm-api/llm_kv_cache_connector.py (1)
36-38: Worker ctor update aligns with base classForwarding llm_args is correct.
svc-trtllm-gh-bot
added
the
Community want to contribute
|
/bot run |
|
PR_Github #17533 [ run ] triggered by Bot |
|
PR_Github #17533 [ run ] completed with state |
|
@Superjomn, I think we need to merge this PR #5911. Then, |
pcastonguay
changed the title
Ok, Marking current MR as Draft until that PR gets merged. |
pcastonguay
force-pushed
the
rihuo/add_llmargs
branch
from
eae0307 to
6afa9ff
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #17933 [ run ] triggered by Bot |
|
PR_Github #17933 [ run ] completed with state |
pcastonguay
changed the title
There was a problem hiding this comment.
@richardhuo-nv now that #5911 has been merged, can we update this PR so that we don't need to explicitely pass tokens_per_block since it's now part of LlmArgs? Thanks.
Signed-off-by: richardhuo-nv <rihuo@nvidia.com> fix Signed-off-by: richardhuo-nv <rihuo@nvidia.com>
Signed-off-by: richardhuo-nv <rihuo@nvidia.com>
Signed-off-by: richardhuo-nv <rihuo@nvidia.com>
richardhuo-nv
force-pushed
the
rihuo/add_llmargs
branch
from
6afa9ff to
440af5f
Compare
Thank you so much for your effort to get the CI passed! I just pushed a commit to rebase the main and removed the tokens_per_block. |
|
/bot run |
|
/bot run --disable-fail-fast |
|
PR_Github #18050 [ run ] triggered by Bot |
|
PR_Github #18050 [ run ] completed with state |
Signed-off-by: richardhuo-nv <rihuo@nvidia.com>
6 participants
Summary by CodeRabbit
Description
Given that executor_config is being deprecated, the connector API needs another information-rich class to provide all the necessary details from the executor. This includes, for example, the Hugging Face model’s configuration, LoRA configuration, MPI world_size and rank, as well as tensor, data, or pipeline parallelism information.
TorchLlmArgs is a good candidate for this role and serves as the successor to executor_config.
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.
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.