xla
xla copied to clipboard
openxla
A machine learning compiler for GPUs, CPUs, and ML accelerators
![copybara-service[bot] avatar](https://avatars.githubusercontent.com/in/44061?v=4 "copybara-service[bot] avatar"){kind=avatar}
Add support for VHLO in XlaCallModuleOp and JAX2TF
[LatencyHidingScheduler] Add early_target_scheduling_rule.
[XLA:CPU Next] Turn matvec with a constant into vecmat Transposing the constant at compile time is free, and vecmat has a much nicer memory access pattern.
[JAX] Split _src/xla_bridge.py into a separate Bazel target. Include _src/distributed.py and _src/clusters/*.py in the same target because they are in a strongly-connected component. [XLA:Python] Set type of ArrayImpl to Any,...
Vendor XLA/TSL into TensorFlow as Bazel dependencies
[XLA] Add `CollectivePermute` op support to pattern matcher.
Choose the same preferred layout for the first dot operand as dot decomposer. The preferred layout should be consistent with what we consider to be a default dot according to...
Add build_test for auto_sharding_runner (CL #2)