refactor: Update decoder buffer and logits management #4450
Conversation
|
/bot run |
|
PR_Github #5746 [ run ] triggered by Bot |
|
PR_Github #5746 [ run ] completed with state |
|
/bot run --disable-fail-fast |
|
PR_Github #5849 [ run ] triggered by Bot |
|
PR_Github #5849 [ run ] completed with state |
Funatiq
force-pushed
the
dev/refactor_decoder_buffers_2
branch
2 times, most recently
from
cc5e39b to
ce13b9e
Compare
|
/bot run |
|
PR_Github #6628 [ run ] triggered by Bot |
|
PR_Github #6628 [ run ] completed with state |
|
/bot run --disable-fail-fast |
|
PR_Github #6783 [ run ] triggered by Bot |
|
PR_Github #6783 [ run ] completed with state |
Funatiq
force-pushed
the
dev/refactor_decoder_buffers_2
branch
from
51f8341 to
693609b
Compare
|
/bot run |
1 similar comment
|
/bot run |
|
PR_Github #7319 [ run ] triggered by Bot |
|
PR_Github #7322 [ run ] triggered by Bot |
|
PR_Github #7319 [ run ] completed with state |
|
PR_Github #7322 [ run ] completed with state |
Funatiq
force-pushed
the
dev/refactor_decoder_buffers_2
branch
from
f1c1043 to
eabbdf8
Compare
|
/bot run |
|
PR_Github #7365 [ run ] triggered by Bot |
|
PR_Github #7365 [ run ] completed with state |
Funatiq
force-pushed
the
dev/refactor_decoder_buffers_2
branch
from
eabbdf8 to
b82d4dd
Compare
|
/bot run |
|
PR_Github #7465 [ run ] triggered by Bot |
|
PR_Github #7465 [ run ] completed with state |
Funatiq
force-pushed
the
dev/refactor_decoder_buffers_2
branch
from
b82d4dd to
2ada5c9
Compare
|
PR_Github #8890 [ run ] completed with state |
Funatiq
force-pushed
the
dev/refactor_decoder_buffers_2
branch
from
47f304e to
2d0fb6b
Compare
|
/bot run |
|
PR_Github #8999 [ run ] triggered by Bot |
|
PR_Github #8999 [ run ] completed with state |
Funatiq
force-pushed
the
dev/refactor_decoder_buffers_2
branch
from
2d0fb6b to
68edea3
Compare
|
/bot run |
|
PR_Github #9058 [ run ] triggered by Bot |
|
PR_Github #9058 [ run ] completed with state |
Funatiq
force-pushed
the
dev/refactor_decoder_buffers_2
branch
from
68edea3 to
02d2b71
Compare
|
/bot run |
|
PR_Github #9131 [ run ] triggered by Bot |
- Moved the handling of logits from `DecoderBuffers` to `DecoderInputBuffers`. - Separated the `DraftBuffers` from `DecoderBuffers` to manage draft token buffers, enhancing the organization of tensor management. - Removed `DecoderBuffers` from function signatures across various components. - Updated Python bindings to reflect changes, maintaining compatibility with existing interfaces. These changes improve the maintainability and clarity of the decoding process in the batch manager. Signed-off-by: Robin Kobus <[email protected]>
Signed-off-by: Robin Kobus <[email protected]>
Signed-off-by: Robin Kobus <[email protected]>
- Modified the `HandleContextLogits` class to accept `max_num_sequences` and return a list of logits tensors along with the logits index. - Adjusted the `HandleGenerationLogits` class to work with the updated logits handling, removing the dependency on `DecoderInputBuffers`. - Updated the `TRTLLMSampler` to accommodate changes in logits management, ensuring proper buffer handling. These changes enhance the clarity and maintainability of the logits processing workflow. Signed-off-by: Robin Kobus <[email protected]>
Funatiq
force-pushed
the
dev/refactor_decoder_buffers_2
branch
from
02d2b71 to
c90f89b
Compare
|
PR_Github #9131 [ run ] completed with state |
|
/bot run |
|
PR_Github #9192 [ run ] triggered by Bot |
|
/bot run |
|
PR_Github #9231 [ run ] triggered by Bot |
|
PR_Github #9231 [ run ] completed with state |
|
/bot run |
|
PR_Github #9235 [ run ] triggered by Bot |
|
PR_Github #9235 [ run ] completed with state |
Description
DecoderBufferstoDecoderInputBuffers.DraftBuffersfromDecoderBuffersto manage draft token buffers, enhancing the organization of tensor management.DecoderBuffersfrom function signatures across various components.Changes to TRTLLMSampler:
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.