[None][chore] rm executor config in kv cache connector #7372
Conversation
leslie-fang25
requested review from
shaharmor98,
laikhtewari,
kaiyux and
QiJune
|
hi @richardhuo-nv, it seems I can't add you as the reviewer. Could you please take a look? |
leslie-fang25
changed the title
📝 WalkthroughWalkthroughConstructors for KV cache connector classes were refactored to remove ExecutorConfig dependencies. Worker constructors are now no-arg; leader/scheduler constructors accept tokens_per_block instead of the full config. create_py_executor updated to submit worker with no args and scheduler with tokens_per_block. Changes
Sequence Diagram(s)sequenceDiagram
participant C as Caller
participant E as create_py_executor
participant T as ThreadPoolExecutor
participant W as worker_cls()
participant S as scheduler_cls(tokens_per_block)
C->>E: create_py_executor(executor_config)
E->>T: start(max_workers=2)
Note over E,T: Root-rank gating for scheduler unchanged
E->>T: submit(worker_cls) %% no args
alt is_root_rank
E->>T: submit(scheduler_cls, executor_config.tokens_per_block)
else not root
Note over E: Scheduler not submitted
end
T-->>E: futures (worker[, scheduler])
E-->>C: instances (worker[, scheduler])
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Tip 🔌 Remote MCP (Model Context Protocol) integration is now available!Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats. ✨ 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
🧹 Nitpick comments (9)
tensorrt_llm/_torch/pyexecutor/kv_cache_connector.py (2)
163-165: Clarify constructor contract for schedulersBase KvCacheConnectorScheduler.init is now no-arg while creator passes tokens_per_block to concrete schedulers. Please document this expectation in the class docstring to prevent confusion and future breakages.
1-2: Update SPDX copyright yearPer guidelines, use current year.
Apply:
-# SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# SPDX-FileCopyrightText: Copyright (c) 2022-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.tensorrt_llm/_torch/pyexecutor/py_executor_creator.py (2)
1-1: Missing SPDX headerAdd NVIDIA SPDX header with current year.
Apply at file top:
+# SPDX-FileCopyrightText: Copyright (c) 2022-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# SPDX-License-Identifier: Apache-2.0 + import copy
30-33: Duplicate import of is_mlais_mla is imported from both ._util and .config_utils; keep one.
Apply:
-from ._util import (KvCacheCreator, _adjust_torch_mem_fraction, - create_py_executor_instance, instantiate_sampler, is_mla) +from ._util import (KvCacheCreator, _adjust_torch_mem_fraction, + create_py_executor_instance, instantiate_sampler) from .config import LoadFormat, PyTorchConfig -from .config_utils import is_mla +from .config_utils import is_mlaexamples/llm-api/llm_kv_cache_connector.py (5)
1-4: Missing SPDX headerAdd NVIDIA SPDX header with current year.
Apply:
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# SPDX-License-Identifier: Apache-2.0 + ### :title KV Cache Connector
22-23: Fix reference: interface file pathPoint to the correct module name.
Apply:
-# See tensorrt_llm/_torch/pyexecutor/connector.py for details about the KV cache connector interface. +# See tensorrt_llm/_torch/pyexecutor/kv_cache_connector.py for details about the KV cache connector interface.
36-38: Worker ctor change—LGTM; add a short docstringDocument that workers are parameterless now.
Apply:
class PersistentKvCacheConnectorWorker(KvCacheConnectorWorker): def __init__(self): + """Parameterless worker. Metadata is provided later via bind_connector_meta().""" super().__init__()
130-135: Make cache keys deterministic across runsPython’s built-in hash is randomized per process; cached files won’t be reusable across new processes. Use a stable digest.
Apply:
+import hashlib @@ - def _hash_tokens(self, tokens: list[int]) -> int: - return abs(hash(tuple(tokens))) + def _hash_tokens(self, tokens: list[int]) -> str: + h = hashlib.sha256() + # Serialize tokens deterministically; 8 bytes per token (little endian) + for t in tokens: + h.update(int(t).to_bytes(8, "little", signed=False)) + return h.hexdigest() @@ - def _file_path(self, hash_value: int) -> Path: - return Path(self.cache_folder) / f"{hash_value}.pt" + def _file_path(self, hash_value: str) -> Path: + return Path(self.cache_folder) / f"{hash_value}.pt"
199-205: Cross-platform module name extractionAvoid hardcoded “/”. Use Path.stem.
Apply:
- this_module = __file__[__file__.rfind("/") + 1:__file__.rfind(".py")] + this_module = Path(__file__).stem
📜 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(2 hunks)tensorrt_llm/_torch/pyexecutor/kv_cache_connector.py(2 hunks)tensorrt_llm/_torch/pyexecutor/py_executor_creator.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.{cpp,cc,cxx,cu,h,hpp,hh,hxx,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.{cpp,cc,cxx,cu,h,hpp,hh,hxx,cuh,py}: Use spaces only; no tabs; indent with 4 spaces
Prepend NVIDIA copyright header (current year) to all source files (.cpp, .h, .cu, .py, etc.)
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: Python code must target Python 3.8+
Indent Python with 4 spaces; no tabs
Preserve module namespaces when importing: from package.subpackage import foo; then call foo.SomeClass() instead of importing the class directly
Python naming: files snake_case; classes PascalCase; functions/methods snake_case; locals snake_case (prefix k_ when starting with a number); globals UPPER_SNAKE_CASE with G_ prefix; constants UPPER_SNAKE_CASE
Avoid shadowing outer-scope variables; initialize all externally visible members in init
Prefer docstrings for interfaces used outside a file; limit comments to function-internal or file-local interfaces
Use Google-style docstrings for classes and functions; document attributes/variables inline so Sphinx can render them
Avoid reflection when simpler alternatives exist; prefer explicit parameters and return dicts over locals()/dynamic tricks
In try/except, catch the narrowest exceptions possible; keep try bodies minimal and use else for the main logic when doing duck-typing checks
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 (1)
tensorrt_llm/_torch/pyexecutor/py_executor_creator.py (1)
tensorrt_llm/_torch/attention_backend/trtllm.py (1)
tokens_per_block(578-582)
⏰ 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). (2)
- GitHub Check: Check PR Checklist Resolution
- GitHub Check: Pre-commit Check
🔇 Additional comments (2)
tensorrt_llm/_torch/pyexecutor/kv_cache_connector.py (1)
83-86: API break resolved—no downstream references toexecutor_configorself._configdetected.tensorrt_llm/_torch/pyexecutor/py_executor_creator.py (1)
412-412: Zero-arg worker instantiation—LGTM; ensure connectors updatedThis assumes all workers have parameterless init. See verification script in kv_cache_connector.py comment.
|
/bot run |
|
PR_Github #16978 [ run ] triggered by Bot |
Signed-off-by: leslie-fang25 <[email protected]>
leslie-fang25
force-pushed
the
leslie/remove_executor_config_in_KvCacheConnector
branch
from
cf1b030 to
b27a7b5
Compare
|
/bot run |
|
PR_Github #16979 [ run ] triggered by Bot |
|
PR_Github #16978 [ run ] completed with state |
|
PR_Github #16979 [ run ] completed with state |
|
/bot run |
|
PR_Github #16986 [ run ] triggered by Bot |
|
PR_Github #16986 [ run ] completed with state |
|
Thank you @leslie-fang25 , as we discussed offline, it would be better if we pass something very informative to the kv_cache_connector, LlmArgs might be a good option to replace executor_config. cc: @pcastonguay |
|
Does LlmArgs contains the information of "tokens per block"? |
I think it has. I am working on a refactor in #7239. After it landed, I think we can use |
Summary by CodeRabbit
Refactor
Chores
Description
Since we are working on to remove
executor configinpy executor, this PR removeexecutor configin the new added kv cache connector.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.