[5830][feat] Improve LoRA cache memory control #1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: qqiao <[email protected]>
…g service (NVIDIA#5234) Signed-off-by: Chuang Zhu <[email protected]>
…IDIA#6000) Signed-off-by: Enwei Zhu <[email protected]>
Signed-off-by: Erin Ho <[email protected]>
…#6101) Signed-off-by: nv-guomingz <[email protected]>
Signed-off-by: Yi Zhang <[email protected]>
…IA#6115) Signed-off-by: Stanley Sun <[email protected]>
…after (NVIDIA#6007) Signed-off-by: ziyixiong-nv <[email protected]>
Signed-off-by: Linda-Stadter <[email protected]>
Signed-off-by: ixlmar <[email protected]>
Signed-off-by: Iman Tabrizian <[email protected]>
Signed-off-by: William Zhang <[email protected]>
Signed-off-by: Frank Di Natale <[email protected]>
NVIDIA#6134) Signed-off-by: qixiang-99 <[email protected]>
…VIDIA#6080) Signed-off-by: Daniel Stokes <[email protected]>
Signed-off-by: Iman Tabrizian <[email protected]>
Signed-off-by: Yifei Zhang <[email protected]>
Signed-off-by: Xavier Simmons <[email protected]>
…in test_e2e (NVIDIA#6140) Signed-off-by: Zhenhuan Chen <[email protected]>
…6106) Signed-off-by: Aurelien Chartier <[email protected]> Co-authored-by: Haohang Huang <[email protected]>
Signed-off-by: Chuang Zhu <[email protected]>
Signed-off-by: Yiqing Yan <[email protected]>
Signed-off-by: tensorrt-cicd <[email protected]> Co-authored-by: tensorrt-cicd <[email protected]>
Signed-off-by: junq <[email protected]>
Signed-off-by: qqiao <[email protected]>
… batch manager (NVIDIA#6055) Signed-off-by: Robin Kobus <[email protected]>
Signed-off-by: leslie-fang25 <[email protected]>
Signed-off-by: Erin Ho <[email protected]>
Signed-off-by: ZhanruiSunCh <[email protected]>
Signed-off-by: Stefan Niebler <[email protected]>
Signed-off-by: yechank <[email protected]>
… tests (NVIDIA#6463) Signed-off-by: Venky Ganesh <[email protected]> Co-authored-by: Larry <[email protected]>
Signed-off-by: peaceh <[email protected]>
Signed-off-by: xinhe-nv <[email protected]>
… in kv cache measure (NVIDIA#6135) Signed-off-by: zhengd-nv <[email protected]>
Signed-off-by: Jinyang Yuan <[email protected]>
) Signed-off-by: William Zhang <[email protected]>
Signed-off-by: junq <[email protected]>
… and allowing lora_config.max_loras and lora_config.max_cpu_loras to override it, changed their default value to None Signed-off-by: Amit Zuker <[email protected]>
… use of LoraConfig and PeftCacheConfig in LLM args Signed-off-by: Amit Zuker <[email protected]>
Signed-off-by: Amit Zuker <[email protected]>
Signed-off-by: Amit Zuker <[email protected]>
Signed-off-by: Amit Zuker <[email protected]>
Signed-off-by: Amit Zuker <[email protected]>
Signed-off-by: Amit Zuker <[email protected]>
Signed-off-by: Amit Zuker <[email protected]>
…clarify test Signed-off-by: Amit Zuker <[email protected]>
… stability Signed-off-by: Amit Zuker <[email protected]>
… LoRA args Signed-off-by: Amit Zuker <[email protected]>
…_loras for stability Signed-off-by: Amit Zuker <[email protected]>
…_percent and host_cache_size, improve device_cache_percent description Signed-off-by: Amit Zuker <[email protected]>
Signed-off-by: Amit Zuker <[email protected]>
…o be non-optional with default values Signed-off-by: Amit Zuker <[email protected]>
Signed-off-by: Amit Zuker <[email protected]>
…rrelevant to pytorch backend Signed-off-by: Amit Zuker <[email protected]>
… PybindMirror, updated its PeftCacheConfig tests accordingly, removed default values from description, raise exception when unused peft_cache_config.lora_prefetch_dir was set instead of writing a warning log message Signed-off-by: Amit Zuker <[email protected]>
Signed-off-by: Amit Zuker <[email protected]>
Signed-off-by: Amit Zuker <[email protected]>
…che sizes, fix incorrect lora request creation Signed-off-by: Amit Zuker <[email protected]>
amitz-nv
force-pushed
the
dev-improve-pytorch-lora-cache-memory-control
branch
from
50e940e to
bce06ad
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
LoraConfig.max_lorasandLoraConfig.max_cpu_lorasto be optional. When they're not set, the cache size would be determined by thePeftCacheConfig, whose existing default values are LoRA GPU cache size is 2% of its free memory, LoRA CPU cache size is 1GiB.lora_config: LoraConfigLLM arg:max_lora_rank,max_loras,max_cpu_loras.Test Coverage
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 [--disable-fail-fast --skip-test --stage-list "A10-1, xxx" --gpu-type "A30, H100_PCIe" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-[Post-Merge]-1, xxx"]Launch build/test pipelines. All previously running jobs will be killed.
--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 "A10-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-1, 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.--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. Will also run 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-[Post-Merge]-1, xxx"(OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-[Post-Merge]-1, xxx".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.