[pull] master from tensorflow:master#46
Merged
pull[bot] merged 10 commits intomcx:masterfrom Dec 13, 2024
Merged
Conversation
PiperOrigin-RevId: 705848817
PiperOrigin-RevId: 705852589
PiperOrigin-RevId: 705865843
Updates LLVM usage to match [5e53a8dadb00](llvm/llvm-project@5e53a8dadb00) PiperOrigin-RevId: 705873858
This also fixes a bug where MLIR optimized a GELU op using a pow op and a mul op. PiperOrigin-RevId: 705884351
The FFI API supports stateful custom calls, but this typically requires that a custom type be registered with the FFI and its "type id" be specified. This change adds a `register_custom_type_id` method to `xla_client` which adds support for this feature via Python.
The API that I settled on was to explicitly pass the required `XLA_FFI_TypeId*` pointer as a PyCapsule, the same way we handle the function pointers:
```
xla_client.register_custom_type_id("custom_type", encapsulated_type_id)
```
where `encapsulated_type_id` is defined something like:
```
nb::capsule(reinterpret_cast<void*>(&MyCustomType::id))
```
PiperOrigin-RevId: 705888170
PiperOrigin-RevId: 705902566
PiperOrigin-RevId: 705902575
… as the crash on Windows is fixed. PiperOrigin-RevId: 705920729
Imported from GitHub PR openxla/xla#20109 - Create a workflow to run OpenXLA CPU/GPU/TPU benchmarks to measure performance improvements and regression. Copybara import of the project: -- 944a401992e46242e40af211d1e0eb07180dbbf4 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Create benchmarks.yml -- 5a31afcfefe05b569b97cb943b66d9f3e882aab8 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update benchmarks.yml -- 551e23791be102e3f105bc407c71e5f3722f50a9 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update benchmarks.yml -- abbc701662100c6b96338f07259408b81b46c0b3 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update benchmarks.yml -- 712c9b866b8f25a4da8c12ef576421b971bf2011 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update benchmarks.yml -- 255a8fff366814e900755b18c591ff6d051f23e9 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update benchmarks.yml -- 9a3bb7d7131c817a2b06ab521a195804511a8ee7 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update benchmarks.yml -- cf95a041a544197ca6f65f1a2443fe0ed7f161c6 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update benchmarks.yml -- da77242e674b1957ea364385676bcf1139461049 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update benchmarks.yml -- b08d632543ee921642bd703f25f80dae7645b44d by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update benchmarks.yml -- e6fc10f8e53c89eef3427d4d35d015982f39df6b by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update and rename benchmarks.yml to cpu_benchmarks.yml -- 4349b2e49f67a9e71ad704f56c38056bd5d7eea2 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update cpu_benchmarks.yml -- bcce7a7e2e604af4f718a6abff98e3e6c937c6a5 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update cpu_benchmarks.yml -- ee5b591e30f87dedccb06e627a3957756084c8a2 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update cpu_benchmarks.yml -- 3ad84596053f0669cbdaa5f9cd02a50b965a25f2 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update cpu_benchmarks.yml -- cd9d339ae0256eb704bd6f53f346f140d112349b by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update cpu_benchmarks.yml -- 4c30d819b4373c981080301974d1ac54db23ccc6 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update cpu_benchmarks.yml -- 7e22bae1a5cde532d1c4473277271c2c35542ec6 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update cpu_benchmarks.yml -- eed90264df299bed261c31b82d598232e296536a by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update cpu_benchmarks.yml -- 03da4b7361f08814e44ef5955a4b241787d03bb2 by Julia Guo <153684546+juliagmt-google@users.noreply.github.com>: Update cpu_benchmarks.yml Merging this change closes #20109 PiperOrigin-RevId: 705927230
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
8 participants
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.
See Commits and Changes for more details.
Created by
pull[bot] (v2.0.0-alpha.1)
Can you help keep this open source service alive? 💖 Please sponsor : )