feat: estimate GPU mem. usage w/ minimal KV cache #4574
Conversation
|
/bot run |
|
PR_Github #6146 [ run ] triggered by Bot |
|
PR_Github #6146 [ run ] completed with state |
ixlmar
force-pushed
the
feat/minimize-temporary-kv-cache
branch
from
deddf23 to
5eed4c2
Compare
|
/bot run |
|
PR_Github #6257 [ run ] triggered by Bot |
|
PR_Github #6257 [ run ] completed with state |
ixlmar
force-pushed
the
feat/minimize-temporary-kv-cache
branch
from
5eed4c2 to
6e623b2
Compare
|
/bot run |
|
/bot kill |
ixlmar
force-pushed
the
feat/minimize-temporary-kv-cache
branch
from
6e623b2 to
e10e7c7
Compare
|
PR_Github #6289 [ run ] triggered by Bot |
|
PR_Github #6290 [ kill ] triggered by Bot |
|
PR_Github #6289 [ run ] completed with state |
|
PR_Github #6290 [ kill ] completed with state |
|
/bot run |
|
PR_Github #6291 [ run ] triggered by Bot |
|
PR_Github #6291 [ run ] completed with state |
|
/bot run |
|
PR_Github #6305 [ run ] triggered by Bot |
|
PR_Github #6305 [ run ] completed with state |
|
/bot run |
|
PR_Github #6313 [ run ] triggered by Bot |
|
PR_Github #6313 [ run ] completed with state |
ixlmar
force-pushed
the
feat/minimize-temporary-kv-cache
branch
from
e10e7c7 to
7800066
Compare
|
/bot run |
|
PR_Github #6476 [ run ] triggered by Bot |
|
PR_Github #6476 [ run ] completed with state |
|
/bot run |
|
PR_Github #6555 [ run ] completed with state |
|
PR_Github #6557 [ kill ] completed with state |
ixlmar
force-pushed
the
feat/minimize-temporary-kv-cache
branch
from
7800066 to
2144a5e
Compare
|
/bot run |
|
PR_Github #6589 [ run ] triggered by Bot |
|
PR_Github #6589 [ run ] completed with state |
ixlmar
force-pushed
the
feat/minimize-temporary-kv-cache
branch
2 times, most recently
from
849ed9c to
7228d5f
Compare
|
/bot reuse-pipeline |
|
PR_Github #6740 [ reuse-pipeline ] triggered by Bot |
|
PR_Github #6740 [ reuse-pipeline ] completed with state |
ixlmar
force-pushed
the
feat/minimize-temporary-kv-cache
branch
from
7228d5f to
c1f5a57
Compare
|
/bot reuse-pipeline |
|
PR_Github #6761 [ reuse-pipeline ] triggered by Bot |
|
PR_Github #6761 [ reuse-pipeline ] completed with state |
Signed-off-by: ixlmar <[email protected]>
ixlmar
force-pushed
the
feat/minimize-temporary-kv-cache
branch
from
c1f5a57 to
4ea7495
Compare
|
/bot reuse-pipeline |
|
PR_Github #7057 [ reuse-pipeline ] triggered by Bot |
|
PR_Github #7057 [ reuse-pipeline ] completed with state |
Signed-off-by: ixlmar <[email protected]> Signed-off-by: darraghdog <[email protected]>
feat: estimate GPU mem. usage w/ minimal KV cache
Description
This improves the accuracy of the estimation of the GPU memory available for KV cache pages (cf.
free_gpu_memory_fractionoption) by performing the estimation with the smallest size possible initial KV cache.Note: Commit b824e44394813ca17192c9ff3dfe8a52920f54ae is from pending PR #4497 and should no longer be part on this PR by the time it is merged.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.