-
Notifications
You must be signed in to change notification settings - Fork 74k
Issues: tensorflow/tensorflow
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Fix api compatibility test for logging to include the use_call_stack argument.
#70904
opened Jul 6, 2024 by
copybara-service
bot
•
Draft
updated Jul 6, 2024
Propagate batch padding policy to SharedBatchScheduler.
#70216
opened Jun 21, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
Pass ModelBatchStats to SharedBatchScheduler.
#70214
opened Jun 21, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
Add support for batch padding policies into SharedBatchScheduler.
#68612
opened May 24, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
Introduce the support for the greedy (kMinimizeTpuCostPerRequest) batch policy.
#68602
opened May 24, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
Introduce the MaybeBatchDown helper method, only supporting BATCH_DOWN at this time.
#66623
opened Apr 29, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
[XLA:GPU] Add num_blocks to TiledHloComputation.
#70897
opened Jul 5, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
Make GPU PJRT client error out early when not compiled with GPU support
#70560
opened Jun 28, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
[XLA:GPU] Make
SoftmaxRewriterTriton
use the new IsTritonSupportedInstruction
, as opposed to the one in legacy_triton::
.
#70895
opened Jul 5, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
[XLA:GPU][NFC] Refactor code to reduce
SoftmaxRewriterTriton::FindAllFusibleDiamondChains
's complexity.
#70896
opened Jul 5, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
Fix compile time regression & re-enable MMA_V3
#70869
opened Jul 4, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
[XLA:CPU] Add runtime check if
set-dimension-size
was rewritten.
#70894
opened Jul 5, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
Clean up
xnnpack_delegate.(cc|h)
.
#70889
opened Jul 5, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
[XLA:CPU] Add runtime check if
get-dimension-size
was rewritten.
#70871
opened Jul 4, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
[XLA:CPU] Refactor
ExecuteState
into a common thunk_utils.h file.
#70887
opened Jul 5, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
[XLA:CPU] Add runtime check if
RngBitGenerator
was expanded.
#70800
opened Jul 3, 2024 by
copybara-service
bot
•
Draft
updated Jul 5, 2024
Reorder methods in RequestCost.
#70877
opened Jul 4, 2024 by
copybara-service
bot
•
Draft
updated Jul 4, 2024
PadThunk implementation in new API
#70874
opened Jul 4, 2024 by
copybara-service
bot
•
Draft
updated Jul 4, 2024
[XLA:GPU] Enable fusing of fp8 matmuls through Triton.
#70873
opened Jul 4, 2024 by
copybara-service
bot
•
Draft
updated Jul 4, 2024
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.