[TRTLLM-6081][Doc] Address review concerns #7382
Conversation
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the ✨ 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
CodeRabbit Configuration File (
|
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
thorjohnsen
changed the title
|
|
||
| KV cache behavior is set by providing the optional argument ```kv_cache_config``` when LLM engine is created. Consider the quickstart example (found in examples/pytorch/quickstart.py): | ||
|
|
||
| ``` |
There was a problem hiding this comment.
Consider adding the python language tag for the literal, i.e. ```python
| llm = LLM(model='TinyLlama/TinyLlama-1.1B-Chat-v1.0', kv_cache_config=kv_cache_config) | ||
| ``` | ||
|
|
||
| You can also set properties after you create KvCacheConfig, for instance |
There was a problem hiding this comment.
- Code quote
KvCacheConfigwith backticks - Start new sentence: "...create
KvCacheConfig, for instance:" --> "...createKvCacheConfig. For example:"
| @@ -0,0 +1,48 @@ | |||
| # How To Change KV Cache Behavior | |||
There was a problem hiding this comment.
"to" is not capitalized in title case: "To" --> "to"
| @@ -0,0 +1,48 @@ | |||
| # How To Change KV Cache Behavior | |||
|
|
|||
| KV cache behavior is set by providing the optional argument ```kv_cache_config``` when LLM engine is created. Consider the quickstart example (found in examples/pytorch/quickstart.py): | |||
There was a problem hiding this comment.
Suggestion:
Set KV cache behavior by providing the optional kv_cache_config argument when you create the LLM engine. Consider the quickstart example found in examples/pytorch/quickstart.py:
| main() | ||
| ``` | ||
|
|
||
| This example runs with default KV cache properties. The default for ```free_gpu_memory_fraction``` is 0.9, which means TRTLLM will try to allocate 90% of free GPU memory for KV cache. Depending on your system, this may be too aggressive, so you decide to dial that back to 0.7. This is done by adding the following lines to the quickstart example: |
There was a problem hiding this comment.
Suggestion:
This example runs with default KV cache properties. The default value for free_gpu_memory_fraction is 0.9, which means TensorRT-LLM tries to allocate 90% of free GPU memory for KV cache. Depending on your system, this allocation can be too aggressive. You can reduce this value to 0.7 by adding the following lines to the quickstart example:
| main() | ||
| ``` | ||
|
|
||
| Here we used a single kv_cache_retention_config object for all the prompts. Alternatively, you can also provide a list, the list must have the same length as the list of prompts. |
There was a problem hiding this comment.
Suggestion:
This example uses a single kv_cache_retention_config object for all the prompts. You can also provide a list that must have the same length as the list of prompts.
docs/source/1.0/features/kvcache.md
Outdated
| ### Retention Policy | ||
|
|
||
| Blocks are assigned priority in line with the [retention policy](llm-api/reference.html#tensorrt_llm.llmapi.KvCacheRetentionConfig) of the request. The retention policy is a list of [TokenRangeRetentionConfig](llm-api/reference.html#tensorrt_llm.llmapi.KvCacheRetentionConfig.KvCacheRetentionConfig) objects, each specifying priority for a given range of tokens, such as "assign priority X to tokens 10 through 61". You can also assign a duration in milliseconds for this to remain in effect, priority will revert to the default after a period of ```duration_ms``` has elapsed from the first time the block was made available for reuse. TokenRangeRetentionConfig only applies to input (prompt) tokens. The property ```decode_retention_policy``` specifies what priority to assign to blocks with generated (decoded) tokens and ```decode_duration_ms``` specifies how long this should remain in effect, after which priority will revert to the default. Default priority is 35. Any property that expects a duration can be set to None, which indicates retention policy never expires. | ||
| Blocks are assigned priority in line with the [retention policy](https://nvidia.github.io/TensorRT-LLM/llm-api/reference.html#tensorrt_llm.llmapi.KvCacheRetentionConfig) of the request. The retention policy is a list of [TokenRangeRetentionConfig](https://nvidia.github.io/TensorRT-LLM/llm-api/reference.html#tensorrt_llm.llmapi.KvCacheRetentionConfig.TokenRangeRetentionConfig) objects, each specifying priority for a given range of tokens, such as "assign priority X to tokens 10 through 61". You can also assign a duration in milliseconds for this to remain in effect, priority will revert to the default after a period of ```duration_ms``` has elapsed from the first time the block was made available for reuse. TokenRangeRetentionConfig only applies to input (prompt) tokens. The property ```decode_retention_policy``` specifies what priority to assign to blocks with generated (decoded) tokens and ```decode_duration_ms``` specifies how long this should remain in effect, after which priority will revert to the default. Default priority is 35. Any property that expects a duration can be set to None, which indicates retention policy never expires. |
There was a problem hiding this comment.
Break into smaller sentences:
"You can also assign a duration in milliseconds for this to remain in effect, priority will revert to the default after a period of duration_ms has elapsed from the first time the block was made available for reuse."
-->
"You can also assign a duration in milliseconds for this to remain in effect. Priority reverts to the default after a period of duration_ms has elapsed from the first time the block was made available for reuse."
"will revert to" --> "reverts to"
docs/source/1.0/features/kvcache.md
Outdated
|
|
||
| ### Speculative Decoding | ||
|
|
||
| Reuse across requests is only supported for one model MTP, all other [speculative decoding](speculative-decoding.md) algorithms must disable block reuse. |
There was a problem hiding this comment.
Break into smaller sentences:
"Reuse across requests is only supported for one model MTP. All other speculative decoding algorithms must disable block reuse."
docs/source/1.0/features/kvcache.md
Outdated
| ## Controlling KV Cache Behavior | ||
|
|
||
| Many of the features in the KV cache system are optional or have user defined properties that alter how they work. Users can control KV cache features through class [KVCacheConfig](llm-api/reference.html#tensorrt_llm.llmapi.KvCacheConfig). The remainder of this section describes how to change the most important behaviors of KV cache system. | ||
| Many of the features in the KV cache system are optional or have user defined properties that alter how they work. Users can control KV cache features through class [KVCacheConfig](https://nvidia.github.io/TensorRT-LLM/llm-api/reference.html#tensorrt_llm.llmapi.KvCacheConfig). The remainder of this section describes how to change the most important behaviors of KV cache system. |
There was a problem hiding this comment.
add "the": "...most important behaviors of KV cache system." --> "...most important behaviors of the KV cache system."
docs/source/1.0/features/kvcache.md
Outdated
| Many of the features in the KV cache system are optional or have user defined properties that alter how they work. Users can control KV cache features through class [KVCacheConfig](llm-api/reference.html#tensorrt_llm.llmapi.KvCacheConfig). The remainder of this section describes how to change the most important behaviors of KV cache system. | ||
| Many of the features in the KV cache system are optional or have user defined properties that alter how they work. Users can control KV cache features through class [KVCacheConfig](https://nvidia.github.io/TensorRT-LLM/llm-api/reference.html#tensorrt_llm.llmapi.KvCacheConfig). The remainder of this section describes how to change the most important behaviors of KV cache system. | ||
|
|
||
| See [this example](../examples/kvcacheconfig.md) of how to use KvCacheConfig to control KV cache behavior. |
There was a problem hiding this comment.
Suggestion:
Refer to How to Change KV Cache Behavior for an example of how to use KvCacheConfig to control KV cache behavior.
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
…nsen/TensorRT-LLM into user/tjohnsen/kvcache_doc_update .
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
thorjohnsen
changed the title
Co-authored-by: Sharan Chetlur <116769508+schetlur-nv@users.noreply.github.com> Signed-off-by: Thor Johnsen <41591019+thorjohnsen@users.noreply.github.com>
Co-authored-by: Sharan Chetlur <116769508+schetlur-nv@users.noreply.github.com> Signed-off-by: Thor Johnsen <41591019+thorjohnsen@users.noreply.github.com>
Co-authored-by: Sharan Chetlur <116769508+schetlur-nv@users.noreply.github.com> Signed-off-by: Thor Johnsen <41591019+thorjohnsen@users.noreply.github.com>
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
mikeiovine
left a comment
mikeiovine
left a comment
There was a problem hiding this comment.
Thanks for fixing the outdated info
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
Signed-off-by: thorjohnsen <41591019+thorjohnsen@users.noreply.github.com>
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
5 participants
@coderabbitai summary
Description
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.