I originally assumed the caller was always providing a full list of replacements but IndexingMap have some uses where the dim_replacement list is empty, resulting in a CHECK-fail.
So, I'm allowing the user to provide either dim or symbol empty lists to ReplaceDimsAndSymbols. In that case, the dims/symbols won't be replaced.
PiperOrigin-RevId: 826138814
The GlobalToLocal and LocalToGlobal custom-calls are for Shardy round trip. These get-tuple-elements will be removed when we import the Shardy dialect and thus they do not need to hold frontend attributes.
This can reduce the size of the generated HLO module text.
PiperOrigin-RevId: 826134489
Instead of 2 ra2a + concat, we can double the output buffer and adjust output offsets. This way we can save on latency by having only one multi-GPU synchronization.
PiperOrigin-RevId: 826122665
- The logic is ported from gemm_fusion_autotuner. I have changed the key of the Key Value store to be just module-fingerprint, earlier it was module-fingerprint + autotunable-fusion-set-from-the-module-fingerprint. The module fingerprint should already represent the fusion-sets contained in it.
- We can improve or just remove this functionality when we design storage for offline autotuning.
PiperOrigin-RevId: 826103885
This prevents max chains of trivial ops (e.g. add.fp32) to run faster than copying the data, which results in 'too fast to measure' error.
PiperOrigin-RevId: 826079017
This change updates the Bazel version used in TensorFlow, JAX, and XLA projects from 7.4.1 to 7.7.0 in `.bazelversion` files and build scripts.
PiperOrigin-RevId: 826075658
Imported from GitHub PR https://github.com/openxla/xla/pull/33278
Bumps [keras](https://github.com/keras-team/keras) from 3.11.3 to 3.12.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a href="https://github.com/keras-team/keras/releases">keras's releases</a>.</em></p>
<blockquote>
<h2>Keras 3.12.0</h2>
<h2>Highlights</h2>
<h3>Keras has a new model distillation API!</h3>
<p>You now have access to an easy-to-use API for distilling large models into small models while minimizing performance drop on a reference dataset -- compatible with all existing Keras models. You can specify a range of different distillation losses, or create your own losses. The API supports multiple concurrent distillation losses at the same time.</p>
<p>Example:</p>
<pre lang="python"><code># Load a model to distill
teacher = ...
# This is the model we want to distill it into
student = ...
<h1>Configure the process</h1>
<p>distiller = Distiller(
teacher=teacher,
student=student,
distillation_losses=LogitsDistillation(temperature=3.0),
)
distiller.compile(
optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy']
)</p>
<h1>Train the distilled model</h1>
<p>distiller.fit(x_train, y_train, epochs=10)
</code></pre></p>
<h3>Keras supports GPTQ quantization!</h3>
<p>GPTQ is now built into the Keras API. GPTQ is a post-training, weights-only quantization method that compresses a model to int4 layer by layer. For each layer, it uses a second-order method to update weights while minimizing the error on a calibration dataset.</p>
<p>Learn how to use it <a href="https://keras.io/guides/gptq_quantization_in_keras/">in this guide</a>.</p>
<p>Example:</p>
<pre lang="python"><code>model = keras_hub.models.Gemma3CausalLM.from_preset("gemma3_1b")
gptq_config = keras.quantizers.GPTQConfig(
dataset=calibration_dataset,
tokenizer=model.preprocessor.tokenizer,
weight_bits=4,
group_size=128,
num_samples=256,
sequence_length=256,
hessian_damping=0.01,
symmetric=False,
</tr></table>
</code></pre>
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a href="adbfd13426"><code>adbfd13</code></a> Add warning to <code>set_backend</code> and more detailed example. (<a href="https://redirect.github.com/keras-team/keras/issues/21787">#21787</a>)</li>
<li><a href="70598b7903"><code>70598b7</code></a> Fix typo in Distiller docstring</li>
<li><a href="eecd34f406"><code>eecd34f</code></a> Fix: <code>keras.ops.quantile</code> works with tf graph execution (<a href="https://redirect.github.com/keras-team/keras/issues/21782">#21782</a>)</li>
<li><a href="c2bc6cfcc7"><code>c2bc6cf</code></a> Suport keras.op.view() to view the same data bitwise at a new dtype (<a href="https://redirect.github.com/keras-team/keras/issues/21763">#21763</a>)</li>
<li><a href="10b51ce5a5"><code>10b51ce</code></a> Make confusion metrics compilable. (<a href="https://redirect.github.com/keras-team/keras/issues/21775">#21775</a>)</li>
<li><a href="18f79d69c9"><code>18f79d6</code></a> Fix negative index handling in MultiHeadAttention attention_axes (<a href="https://redirect.github.com/keras-team/keras/issues/21721">#21721</a>)</li>
<li><a href="18e0364cbc"><code>18e0364</code></a> Support for extracting volume patches (<a href="https://redirect.github.com/keras-team/keras/issues/21759">#21759</a>)</li>
<li><a href="dc5e42cca4"><code>dc5e42c</code></a> fix sas metrics in jax <code>fit</code> (<a href="https://redirect.github.com/keras-team/keras/issues/21765">#21765</a>)</li>
<li><a href="1ba3b8f896"><code>1ba3b8f</code></a> Fix discretization discrepancy (<a href="https://redirect.github.com/keras-team/keras/issues/21769">#21769</a>)</li>
<li><a href="53987a768d"><code>53987a7</code></a> Document that <code>set_backend</code> requires re-importing keras. (<a href="https://redirect.github.com/keras-team/keras/issues/21764">#21764</a>)</li>
<li>Additional commits viewable in <a href="https://github.com/keras-team/keras/compare/v3.11.3...v3.12.0">compare view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/openxla/xla/network/alerts).
</details>
Copybara import of the project:
--
b37d94a32428d62ed3e73765f4e7b61bc6ed8549 by dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>:
Bump keras in /xla/backends/cpu/benchmarks/e2e/gemma2/keras
Bumps [keras](https://github.com/keras-team/keras) from 3.11.3 to 3.12.0.
- [Release notes](https://github.com/keras-team/keras/releases)
- [Commits](https://github.com/keras-team/keras/compare/v3.11.3...v3.12.0)
---
updated-dependencies:
- dependency-name: keras
dependency-version: 3.12.0
dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com>
Merging this change closes#33278
PiperOrigin-RevId: 826053656
Symbolic dimensions and symbols are both implemented as SymbolicExpr variables, with symbols being offset by the number of dimensions. This implementation detail was previously exposed to users of SymbolicExprContext, who had to manually calculate variable IDs. I ended having a hidden bug in the implementation of IndexingMap, so I included these free functions to make the translation less bug-prone.
The SymbolicMap tests have been updated to use these new helper functions
PiperOrigin-RevId: 826053249
Add CustomCallThunk::OwnedHandlerBundle, a bag of `unique_ptr<ffi::Ffi>` that
enable using lambdas with captures in CustomCallThunk. Lambda captures must
outlive the created thunk.
The functionality is similar to what is possible with "old-style" callbacks,
but doesn't depend on them, and adds support for other handlers available via
XLA_FFI_Handler_Bundle.
PiperOrigin-RevId: 826043689
This change implements AbslHashValue and llvm::hash_value for xla::gpu::SymbolicMap.
This is a prerequisite for correctly implementing AbslHashValue for xla::IndexingMap after its internal migration to use SymbolicMap. Specifically, it needs be used in IndexingMap::AbslHashValue.
PiperOrigin-RevId: 826038011
`ffi::Attribute` and related types are members of the `CustomCallThunk`. Therefore we need to be able to serialize these types to proto message if we wanna be able to serialize instances of CustomCallThunk.
So this change is adding proto message representation of the types and adds functions `ToProto` and `FromProto` to each of them. Most of the types are currently defined as type aliases of some `std::variant` instantiation. This changes replaces the aliases by classes which inherit from the std::variant type. These new types then get the proto serialization functions.
PiperOrigin-RevId: 826035931
ragged-all-to-all can be used in two pattern:
1. If input size if smaller than the output, we assume that it's a dispatch phase where input is dense and we're distributing data.
2. If output size if smaller, we assume that input is padded and we're gathering data, distributed with the first pattern.
Original decomposer was optimized for dispatch case, because it did cross-host all-gather of dense input It's not optimal for the combine phase, because it results it transferring a lot of padding cross host.
A more optimal set of operations is to do local partial ragged-all-to-all, exchange partial results, and apply them locally.
PiperOrigin-RevId: 826035358
Similarly to GetAffineConstantExpr, I'm introducing GetSymbolicConstantExpr/s to create constants of SymbolicExpr from a list of values.
PiperOrigin-RevId: 826020777
We need a proper base class for common functionality. `CollectiveOpsTestE2E` is not a good base class, because it also holds a lot of fp8-specific helpers that are only used in a few tests.
PiperOrigin-RevId: 826017075
A function similar to ForAllThunksMutable, but capable of wrapping or replacing nested thunks with new ones. In case the thunk has some specific requirements (e.g. assumes the directly nested thunk is a `SequentialThunk`), the implementation needs to ensure the assumptions still hold. The transform function must be infallible, but it may be a no-op and return the original `unique_ptr<Thunk>`.
The use for this is in buffer checksumming: to cover all thunks, we need to recursively insert pre-/post-execution checksum thunks around execution of nested thunks. Unfortunately, ForAllThunksMutable doesn't allow mutating the thunk's *container*, which would create the need to switch() over thunk kind, special-case any thunk that may contain nested thunks, and expose the internals to the caller to reimplement the recursion.
PiperOrigin-RevId: 826014413
Imported from GitHub PR https://github.com/openxla/xla/pull/33188📝 Summary of Changes
Fix tests when executing on rbe
🎯 Justification
Fix hermetic dependencies so right libs are loaded.
Libs are put as a data dependency as many of the rocm libs may have their own
RPATH=$ORIGIN/..., they will try to load the libs from the place where they are.
This leads to a situation that one lib located in _solid_data dir will try to find its
dependencies in the same dir. However dependency might be located in the data
directory. Then either test can't load the lib or tries to load one from the system libs.
🚀 Kind of Contribution
Please remove what does not apply: 🐛 Bug Fix
📊 Benchmark (for Performance Improvements)
Build fix
🧪 Unit Tests:
Build fix
🧪 Execution Tests:
Build fix
Copybara import of the project:
--
43913bfbacc042c7a81e692cfa28e0a0733c3989 by Alexandros Theodoridis <atheodor@amd.com>:
Add minimal hip runtime deps to kernel_headers
--
ffb62f536608b00445fda4fce0a3323c5bf6fe9d by Alexandros Theodoridis <atheodor@amd.com>:
Fix hermetic build invalid local rpath
Merging this change closes#33188
PiperOrigin-RevId: 826014075
This change allows broadcast and reshape operations on the scale operands of `scaled-dot` to be fused into the Triton kernel. It generalizes the operand fusion logic to handle all four operands of `scaled-dot` and adds support for `BroadcastOp` and `ExpandDimsOp` in the Triton MLIR conversion. A new test case is added to verify this fusion.
PiperOrigin-RevId: 826012089
Currently it is assumed that GetTupleElement is never the root of a
computation. That assumption is not necessarily true, e.g. during autotuning of
Cublas Gemm calls we can have a GetTupleElement op as root.
PiperOrigin-RevId: 825932301
* Extend alternate memory chunk reservations for aliased uses.
* Add pinned allocations in alternate memory for aliased uses.
* Mark all aliased allocations as colocated.
Pin all values aliased with the prefetched source value to default memory.
PiperOrigin-RevId: 825801181
It is pure mechanical move cl.
The goal is to use the pass for all the buffer debug checks. We have checksum and nan_counter kernels at the moment.
PiperOrigin-RevId: 825602375
Imported from GitHub PR https://github.com/openxla/xla/pull/33085📝 Summary of Changes
Fix too strict spawn strategy for rbe builds
🎯 Justification
remote only execution is not possible for all the tests
🚀 Kind of Contribution
Please remove what does not apply: 🐛 Bug Fix
📊 Benchmark (for Performance Improvements)
Not relevant
🧪 Unit Tests:
Not relevant
🧪 Execution Tests:
Not relevant
Copybara import of the project:
--
df73e6e006c47d5ada1e14ced8f2ae94c0df7dd8 by Alexandros Theodoridis <atheodor@amd.com>:
Fix too strict default spanw strategy for rbe builds
Merging this change closes#33085
PiperOrigin-RevId: 825463234
Encoding extra metadata about an debug log entry within its ID limits how much
information we can pass. To remove the limitation without the need to pass
extra data between host and device, introduce a metadata store that provides a
opaque ID -> metadata mapping.
Follow up patches will make checksum/NaN tracing use
BufferDebugLogEntryMetadataStore shared between all thunks that operate on
BufferDebugLog:
- BuffersChecksumThunks put the metadata into the store and use the returned
entry_ids to identify the checksums from BufferDebugLog,
- xla_gpu_buffer_debug_log_dump reads the BufferDebugLog and uses the store to
resolve the entry_ids into the metadata.
PiperOrigin-RevId: 825462635
Imported from GitHub PR https://github.com/openxla/xla/pull/33141
Bumps [github/codeql-action](https://github.com/github/codeql-action) from 4.30.9 to 4.31.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a href="https://github.com/github/codeql-action/releases">github/codeql-action's releases</a>.</em></p>
<blockquote>
<h2>v4.31.0</h2>
<h1>CodeQL Action Changelog</h1>
<p>See the <a href="https://github.com/github/codeql-action/releases">releases page</a> for the relevant changes to the CodeQL CLI and language packs.</p>
<h2>4.31.0 - 24 Oct 2025</h2>
<ul>
<li>Bump minimum CodeQL bundle version to 2.17.6. <a href="https://redirect.github.com/github/codeql-action/pull/3223">#3223</a></li>
<li>When SARIF files are uploaded by the <code>analyze</code> or <code>upload-sarif</code> actions, the CodeQL Action automatically performs post-processing steps to prepare the data for the upload. Previously, these post-processing steps were only performed before an upload took place. We are now changing this so that the post-processing steps will always be performed, even when the SARIF files are not uploaded. This does not change anything for the <code>upload-sarif</code> action. For <code>analyze</code>, this may affect Advanced Setup for CodeQL users who specify a value other than <code>always</code> for the <code>upload</code> input. <a href="https://redirect.github.com/github/codeql-action/pull/3222">#3222</a></li>
</ul>
<p>See the full <a href="https://github.com/github/codeql-action/blob/v4.31.0/CHANGELOG.md">CHANGELOG.md</a> for more information.</p>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a href="https://github.com/github/codeql-action/blob/main/CHANGELOG.md">github/codeql-action's changelog</a>.</em></p>
<blockquote>
<h1>CodeQL Action Changelog</h1>
<p>See the <a href="https://github.com/github/codeql-action/releases">releases page</a> for the relevant changes to the CodeQL CLI and language packs.</p>
<h2>[UNRELEASED]</h2>
<p>No user facing changes.</p>
<h2>4.31.0 - 24 Oct 2025</h2>
<ul>
<li>Bump minimum CodeQL bundle version to 2.17.6. <a href="https://redirect.github.com/github/codeql-action/pull/3223">#3223</a></li>
<li>When SARIF files are uploaded by the <code>analyze</code> or <code>upload-sarif</code> actions, the CodeQL Action automatically performs post-processing steps to prepare the data for the upload. Previously, these post-processing steps were only performed before an upload took place. We are now changing this so that the post-processing steps will always be performed, even when the SARIF files are not uploaded. This does not change anything for the <code>upload-sarif</code> action. For <code>analyze</code>, this may affect Advanced Setup for CodeQL users who specify a value other than <code>always</code> for the <code>upload</code> input. <a href="https://redirect.github.com/github/codeql-action/pull/3222">#3222</a></li>
</ul>
<h2>4.30.9 - 17 Oct 2025</h2>
<ul>
<li>Update default CodeQL bundle version to 2.23.3. <a href="https://redirect.github.com/github/codeql-action/pull/3205">#3205</a></li>
<li>Experimental: A new <code>setup-codeql</code> action has been added which is similar to <code>init</code>, except it only installs the CodeQL CLI and does not initialize a database. Do not use this in production as it is part of an internal experiment and subject to change at any time. <a href="https://redirect.github.com/github/codeql-action/pull/3204">#3204</a></li>
</ul>
<h2>4.30.8 - 10 Oct 2025</h2>
<p>No user facing changes.</p>
<h2>4.30.7 - 06 Oct 2025</h2>
<ul>
<li>[v4+ only] The CodeQL Action now runs on Node.js v24. <a href="https://redirect.github.com/github/codeql-action/pull/3169">#3169</a></li>
</ul>
<h2>3.30.6 - 02 Oct 2025</h2>
<ul>
<li>Update default CodeQL bundle version to 2.23.2. <a href="https://redirect.github.com/github/codeql-action/pull/3168">#3168</a></li>
</ul>
<h2>3.30.5 - 26 Sep 2025</h2>
<ul>
<li>We fixed a bug that was introduced in <code>3.30.4</code> with <code>upload-sarif</code> which resulted in files without a <code>.sarif</code> extension not getting uploaded. <a href="https://redirect.github.com/github/codeql-action/pull/3160">#3160</a></li>
</ul>
<h2>3.30.4 - 25 Sep 2025</h2>
<ul>
<li>We have improved the CodeQL Action's ability to validate that the workflow it is used in does not use different versions of the CodeQL Action for different workflow steps. Mixing different versions of the CodeQL Action in the same workflow is unsupported and can lead to unpredictable results. A warning will now be emitted from the <code>codeql-action/init</code> step if different versions of the CodeQL Action are detected in the workflow file. Additionally, an error will now be thrown by the other CodeQL Action steps if they load a configuration file that was generated by a different version of the <code>codeql-action/init</code> step. <a href="https://redirect.github.com/github/codeql-action/pull/3099">#3099</a> and <a href="https://redirect.github.com/github/codeql-action/pull/3100">#3100</a></li>
<li>We added support for reducing the size of dependency caches for Java analyses, which will reduce cache usage and speed up workflows. This will be enabled automatically at a later time. <a href="https://redirect.github.com/github/codeql-action/pull/3107">#3107</a></li>
<li>You can now run the latest CodeQL nightly bundle by passing <code>tools: nightly</code> to the <code>init</code> action. In general, the nightly bundle is unstable and we only recommend running it when directed by GitHub staff. <a href="https://redirect.github.com/github/codeql-action/pull/3130">#3130</a></li>
<li>Update default CodeQL bundle version to 2.23.1. <a href="https://redirect.github.com/github/codeql-action/pull/3118">#3118</a></li>
</ul>
<h2>3.30.3 - 10 Sep 2025</h2>
<p>No user facing changes.</p>
<h2>3.30.2 - 09 Sep 2025</h2>
<ul>
<li>Fixed a bug which could cause language autodetection to fail. <a href="https://redirect.github.com/github/codeql-action/pull/3084">#3084</a></li>
<li>Experimental: The <code>quality-queries</code> input that was added in <code>3.29.2</code> as part of an internal experiment is now deprecated and will be removed in an upcoming version of the CodeQL Action. It has been superseded by a new <code>analysis-kinds</code> input, which is part of the same internal experiment. Do not use this in production as it is subject to change at any time. <a href="https://redirect.github.com/github/codeql-action/pull/3064">#3064</a></li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a href="4e94bd11f7"><code>4e94bd1</code></a> Merge pull request <a href="https://redirect.github.com/github/codeql-action/issues/3235">#3235</a> from github/update-v4.31.0-1d36546c1</li>
<li><a href="8f11182164"><code>8f11182</code></a> Update changelog for v4.31.0</li>
<li><a href="1d36546c14"><code>1d36546</code></a> Merge pull request <a href="https://redirect.github.com/github/codeql-action/issues/3234">#3234</a> from github/mbg/changelog/post-processing</li>
<li><a href="08ada26e6a"><code>08ada26</code></a> Add changelog entry for post-processing change</li>
<li><a href="b843cbeed0"><code>b843cbe</code></a> Merge pull request <a href="https://redirect.github.com/github/codeql-action/issues/3233">#3233</a> from github/mbg/getOptionalEnvVar</li>
<li><a href="1ecd563919"><code>1ecd563</code></a> Use <code>getOptionalEnvVar</code> in <code>writePostProcessedFiles</code></li>
<li><a href="e576807920"><code>e576807</code></a> Merge pull request <a href="https://redirect.github.com/github/codeql-action/issues/3223">#3223</a> from github/henrymercer/bump-minimum</li>
<li><a href="ad35676669"><code>ad35676</code></a> Add <code>getOptionalEnvVar</code> function</li>
<li><a href="d75645b13f"><code>d75645b</code></a> Merge pull request <a href="https://redirect.github.com/github/codeql-action/issues/3222">#3222</a> from github/mbg/upload-lib/post-process</li>
<li><a href="710606cc35"><code>710606c</code></a> Check that <code>outputPath</code> is non-empty</li>
<li>Additional commits viewable in <a href="16140ae1a1...4e94bd11f7">compare view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
</details>
Copybara import of the project:
--
cbe7908eed34d441708d7360f23dad04e5b48ee1 by dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>:
Bump github/codeql-action from 4.30.9 to 4.31.0
Bumps [github/codeql-action](https://github.com/github/codeql-action) from 4.30.9 to 4.31.0.
- [Release notes](https://github.com/github/codeql-action/releases)
- [Changelog](https://github.com/github/codeql-action/blob/main/CHANGELOG.md)
- [Commits](16140ae1a1...4e94bd11f7)
---
updated-dependencies:
- dependency-name: github/codeql-action
dependency-version: 4.31.0
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com>
Merging this change closes#33141
PiperOrigin-RevId: 825449574
Imported from GitHub PR https://github.com/openxla/xla/pull/33205📝 Summary of Changes
The simplification was unintentionally disabled in
2accf052cb.
🎯 Justification
Bug fix.
🚀 Kind of Contribution
🐛 Bug Fix, ⚡️ Performance Improvement
📊 Benchmark (for Performance Improvements)
No
🧪 Unit Tests:
Yes.
🧪 Execution Tests:
No.
Copybara import of the project:
--
2fb682c10ff49212044dd995ba97aa329e52bb71 by Ilia Sergachev <isergachev@nvidia.com>:
[GPU] Fix reduce-precision simplification.
Was unintentionally disabled in
2accf052cb.
Merging this change closes#33205
PiperOrigin-RevId: 825449067
* Extend alternate memory chunk reservations for aliased uses.
* Add pinned allocations in alternate memory for aliased uses.
* Mark all aliased allocations as colocated.
Pin all values aliased to the left of the source hlo value being block prefetched to default memory, values aliased to the right of the source hlo value will be pinned to default memory in all cases except - when a scheduling a new prefetch is successful.
* For source values, if a pinned allocation exists and adding uses to the allocation is required.
* For other (aliased) values finalizing the value suffices.
Misc:
* When creating colocated aliased allocations in alternate memory, do not rely on getting the first colocated block from the back of the list.
* Code cleanup.
PiperOrigin-RevId: 825302368
This change removes the deprecated `Shape(const ShapeProto&)` constructor and updates its call sites to use `Shape::FromProto` instead, which returns a `StatusOr<Shape>`. The call sites now explicitly handle the potential error status.
PiperOrigin-RevId: 825288664
This prints the entire instruction instead of instruction name when the original value has a different tuple structure with the instruction shape in HLO verifier pass. The instruction name is not reliable and could be different from its name in the HLO dump.
PiperOrigin-RevId: 825241833
This changes the predicates for calling a library for a dot to indicate whether we will actually call the library, not just whether the library supports the dot. This fixes bugs where we incorrectly claim a library will handle the dot.
PiperOrigin-RevId: 825231317
