| COMMIT |
0.70 |
Refactor Subgraph construction to use std::make_unique |
|
Explicitly states 'This change is AI gen |
2026-04-13 |
| COMMIT |
0.60 |
Automated Code Change |
|
Generic title 'Automated Code Change' la |
2026-04-14 |
| COMMIT |
0.30 |
Automated Code Change |
|
Generic, fully automated message may ind |
2026-04-14 |
| COMMIT |
0.30 |
Automated Code Change |
|
Generic, fully automated message may ind |
2026-04-14 |
| COMMIT |
0.30 |
Automated Code Change |
|
Generic, fully automated message may ind |
2026-04-14 |
| COMMIT |
0.30 |
Automated Code Change |
|
Generic, fully automated message may ind |
2026-04-14 |
| COMMIT |
0.30 |
Automated Code Change |
|
Generic, fully automated message may ind |
2026-04-14 |
| COMMIT |
0.20 |
Automated Code Change |
|
Very generic boilerplate, but lacks expl |
2026-04-14 |
| COMMIT |
0.10 |
PR #40585: Cross Host Data Transfers: Unify Prepared{Send,Re |
|
Uses template and detailed explanation, |
2026-04-14 |
| PR |
0.10 |
Improve AutoGraph if-expression error for mismatched branche |
|
Standard changelog with domain details; |
2026-04-02 |
| COMMIT |
0.00 |
Add prefetch to testTakeWithRestartedWorker. |
|
Concise commit message, typical human st |
2026-04-14 |
| COMMIT |
0.00 |
Edit evaluator to allow a specific custom call |
|
Brief, technical edit description; reads |
2026-04-14 |
| COMMIT |
0.00 |
port EmitPadToStaticLLVMIR to produce KernelDefinition |
|
Porting statement, ultra terse; human st |
2026-04-14 |
| COMMIT |
0.00 |
port EmitRngGetAndUpdateStateLLVMIR to produce KernelDefinit |
|
Porting description, very brief and tech |
2026-04-14 |
| COMMIT |
0.00 |
Fix failure of nnapi_delegate_test.cc due to float rounding. |
|
Standard fix message with specific file |
2026-04-14 |
| COMMIT |
0.00 |
[XLA:GPU] Introduce strong type for tiled dimension IDs and |
|
Technical commit with domain terms; conc |
2026-04-14 |
| COMMIT |
0.00 |
Default users of GetTfrtGpuClient(options) to |
|
Technical defaulting statement, naturall |
2026-04-14 |
| COMMIT |
0.00 |
Refactor `SpmdPartitioner::ConvertUnreducedSubgroup` to use |
|
Refactoring message, directly references |
2026-04-14 |
| COMMIT |
0.00 |
[PjRt-IFRT] Check that just one serialized_descriptor is pas |
|
Technical commit, updates documentation, |
2026-04-14 |
| COMMIT |
0.00 |
Check for coordination service incarnation mismatches. |
|
Technical, informal, minor typo, domain- |
2026-04-14 |
| COMMIT |
0.00 |
make sort emitter async |
|
Short, standard, informal lowercase, cle |
2026-04-14 |
| COMMIT |
0.00 |
Introducing option to control the number of window prefetche |
|
Concise, informal, uses 'Introducing', h |
2026-04-14 |
| COMMIT |
0.00 |
[XLA:GPU] do not create regions for reduce arguments |
|
Technical, domain-specific, informal wit |
2026-04-14 |
| COMMIT |
0.00 |
Use constexpr `absl::string_view` instead of `char` as per g |
|
Brief, domain-specific, conforms to huma |
2026-04-14 |
| COMMIT |
0.00 |
[XLA] Make sure that executable serialization is determinist |
|
Technical, to-the-point, domain-specific |
2026-04-14 |
| COMMIT |
0.00 |
[XLA:GPU] Retire xla_gpu_experimental_enable_split_k_rewrite |
|
Domain-specific, concise, casual phrasin |
2026-04-14 |
| COMMIT |
0.00 |
[XLA:GPU] Update default Triton autotuner configs for B200. |
|
Very short, technical, human commit mess |
2026-04-14 |
| COMMIT |
0.00 |
PR #40656: [GPU] Wire deadlock prevention for async collecti |
|
Has template-like structure, but filled |
2026-04-14 |
| COMMIT |
0.00 |
[XLA:GPU] Remove range_mapped option from multicast memory r |
|
Brief, domain-specific, standard human c |
2026-04-14 |
| COMMIT |
0.00 |
[XLA:GPU] Add a debug option to force a specific split_k val |
|
Technical, concise, domain-specific; no |
2026-04-14 |
| COMMIT |
0.00 |
Migrate remaining codegen users to use IndexingMap::Symbolic |
|
Informal tone, includes typos and smiley |
2026-04-14 |
| COMMIT |
0.00 |
[XLA:GPU] Emit bitcast with the new tiling. |
|
Terse, technical commit; no AI indicator |
2026-04-14 |
| COMMIT |
0.00 |
PR #40878: [stream_executor] Fix DCHECK in CommandBufferTh |
|
Detailed, domain-specific explanation; n |
2026-04-14 |
| COMMIT |
0.00 |
Migrate and remove IndexingMap::ConstraintsSatisfied(AffineE |
|
Concise, technical migration summary; hu |
2026-04-14 |
| COMMIT |
0.00 |
Regenerate warnings file. |
|
Terse, imperative; typical human commit |
2026-04-14 |
| COMMIT |
0.00 |
PR #40847: [ROCm] Fix LoadKernel to use refcounted module pa |
|
Somewhat formal, but includes technical |
2026-04-14 |
| COMMIT |
0.00 |
PR #40838: Canonicalize custom element sizes on tuple leaf a |
|
Detailed technical explanation, lacks AI |
2026-04-14 |
| COMMIT |
0.00 |
PR #40849: [xla:gpu] Remove unused IsNestedCommandBuffer API |
|
Simple, factual, codebase maintenance; h |
2026-04-14 |
| COMMIT |
0.00 |
Improve BroadcastCanonicalizer to create a transpose for the |
|
Concise technical description with minim |
2026-04-14 |
| COMMIT |
0.00 |
PR #35304: [XLA:GPU] [plugin] Adding sycl/oneapi plugin supp |
|
Migrated PR/changelogs with technical su |
2026-04-14 |
| COMMIT |
0.00 |
[XLA:PJRT] Align collective memory with respect to library s |
|
Technical, precise, and succinct; no AI |
2026-04-14 |
| COMMIT |
0.00 |
[XLA:GPU] Remove deprecated usages of SynchronousMemZero. |
|
Technical description, terse, no formal |
2026-04-14 |
| COMMIT |
0.00 |
[XLA:GPU] Express bitcast tiling via transpose and reshape t |
|
Brief, technical note with clear human w |
2026-04-14 |
| COMMIT |
0.00 |
PR #40854: [xla:gpu] Use fast fingerprint for scheduling XLA |
|
Technical summary with informal exclamat |
2026-04-14 |
| COMMIT |
0.00 |
PR #40832: [XLA:GPU][oneAPI ]Add SYCL platform support to HL |
|
Technical content, migration context, so |
2026-04-14 |
| COMMIT |
0.00 |
Prevent metadata id overlap between the cupti collector and |
|
Direct technical fix, no formal or gener |
2026-04-14 |
| COMMIT |
0.00 |
PR #35304: [XLA:GPU] [plugin] Adding sycl/oneapi plugin supp |
|
Matches #2, technical migration logs, no |
2026-04-14 |
| COMMIT |
0.00 |
Migrate and remove IndexingMap::GetConstraints |
|
Domain-specific, informal, contains a ty |
2026-04-14 |
| COMMIT |
0.00 |
PR #40667: [xla:gpu] Cleanup GPU thunk APIs |
|
Detailed technical changelog; no AI-spec |
2026-04-14 |
| COMMIT |
0.00 |
Migrate codegen/tiling to SymbolicMap |
|
Informal, domain-specific, uses jargon a |
2026-04-14 |
| COMMIT |
0.00 |
[XLA:GPU] Use single D2D copy which also zeroes untouched by |
|
Brief, domain-specific summary with no A |
2026-04-14 |
| COMMIT |
0.00 |
Reverts 4908d3a6ff47893a5e7a38172c42adfeabcc7992 |
|
Standard terse reversion message, clearl |
2026-04-14 |
| COMMIT |
0.00 |
Automated Code Change |
|
Message is an automated commit; no AI si |
2026-04-14 |
| COMMIT |
0.00 |
Automated Code Change |
|
Message is an automated commit; no AI si |
2026-04-14 |
| COMMIT |
0.00 |
Automated Code Change |
|
Message is an automated commit; no AI si |
2026-04-14 |
| COMMIT |
0.00 |
Remove redundant dot_operation_single_threaded_runtime_test. |
|
Technical and concise with domain-specif |
2026-04-14 |
| COMMIT |
0.00 |
Automated Code Change |
|
Message is an automated commit; no AI si |
2026-04-14 |
| COMMIT |
0.00 |
Automated Code Change |
|
Message is an automated commit; no AI si |
2026-04-14 |
| COMMIT |
0.00 |
Automated Code Change |
|
Message is an automated commit; no AI si |
2026-04-14 |
| COMMIT |
0.00 |
Automated Code Change |
|
Message is an automated commit; no AI si |
2026-04-14 |
| COMMIT |
0.00 |
Automated Code Change |
|
Message is an automated commit; no AI si |
2026-04-14 |
| COMMIT |
0.00 |
Automated Code Change |
|
Message is an automated commit; no AI si |
2026-04-14 |
| COMMIT |
0.00 |
Automated Code Change |
|
Generic commit title with no AI stylisti |
2026-04-14 |
| COMMIT |
0.00 |
Avoid overflow when casting an odd number of int4s |
|
Concise, technical commit message with d |
2026-04-14 |
| COMMIT |
0.00 |
PR #40738: [xla:gpu] Optimize hot path for requesting GpuCli |
|
Technical PR description, informal and f |
2026-04-14 |
| COMMIT |
0.00 |
XLA:PJRT: Optimize 1-byte transposes with 16x16 SIMD kernels |
|
Technical description with specific numb |
2026-04-13 |
| COMMIT |
0.00 |
PR #40751: [xla:gpu] Delete special case for calls to comman |
|
Casual tone, domain-specific context, no |
2026-04-13 |
| COMMIT |
0.00 |
Roll-forward with fix. Allow async slice conversion candidat |
|
Standard brief technical commit, no AI s |
2026-04-13 |
| COMMIT |
0.00 |
Move rules_ml_toolchain loading from WORKSPACE and workspace |
|
Somewhat formal but uses project-specifi |
2026-04-13 |
| COMMIT |
0.00 |
Remove unused SynchronousMemZero from PluggableDeviceStreamE |
|
Terse, technical, typical of human commi |
2026-04-13 |
| COMMIT |
0.00 |
[XLA:GPU] Use maximum clique to allocate scratch buffer. |
|
Short, technical commit, no signs of AI |
2026-04-13 |
| COMMIT |
0.00 |
Check if hlo_live_range_ in buffer assignment is valid befor |
|
Direct and minimal technical update, no |
2026-04-13 |
| COMMIT |
0.00 |
PR #39926: Improvements to the HBM OOM Error page (Error E10 |
|
Uses template, but free-text is concise |
2026-04-13 |
| COMMIT |
0.00 |
Handle unregistered dialects as part of unstable dialects |
|
Brief, technical, human-like summary. |
2026-04-13 |
| COMMIT |
0.00 |
[XLA:MSA] Minor test updates, make operand op code optional |
|
Standard terse commit, human style, no A |
2026-04-13 |
| COMMIT |
0.00 |
Fix unchecked return values of MarkSubgraphAsDelegationSkipp |
|
Terse, technical commit message typical |
2026-04-13 |
| COMMIT |
0.00 |
Replace `MultiplyAndCheckOverflow` with `CheckedInt` in full |
|
Concise technical phrasing, no AI signal |
2026-04-13 |
| COMMIT |
0.00 |
Pjrt: Pipe `total_allocation_bytes`, `indefinite_allocations |
|
Jargon-rich, specific, human-written sty |
2026-04-13 |
| COMMIT |
0.00 |
Handle `HloShardingV3` for `Manual`/`Unreduced` Subgroups |
|
Brief, domain-specific, lacks AI hallmar |
2026-04-13 |
| COMMIT |
0.00 |
Add more performance microbenchmarks for SlinkyThreadPool |
|
Short, informal, fits human commit norms |
2026-04-13 |
| COMMIT |
0.00 |
Make GetCompiledMemoryStats export additional fields. |
|
Template changelog, concise edit summary |
2026-04-13 |
| COMMIT |
0.00 |
PR #40676: [xla:gpu] Add connected-components permute under |
|
PR includes template, human-authored det |
2026-04-13 |
| COMMIT |
0.00 |
pjrt_compiler: Provide a mechanism for fallible casts to PjR |
|
Technical explanation, natural human wri |
2026-04-13 |
| COMMIT |
0.00 |
Handle size 1 axis in `IsManual`/`IsUnreduced` checks |
|
Minimalist, domain-specific, clearly hum |
2026-04-13 |
| COMMIT |
0.00 |
[stablehlo] Only call isLegalLocation in debug mode. |
|
Informal, justified change, typical huma |
2026-04-13 |
| COMMIT |
0.00 |
Handle axis of size 1 in `V3ToV2Sharding` |
|
Technical jargon and typo indicate human |
2026-04-13 |
| COMMIT |
0.00 |
PR #33240: Adding a delayMoveToHost heuristic to LHS and rel |
|
Structured with template sections, some |
2026-04-13 |
| COMMIT |
0.00 |
Only implicitly convert from type that are convertible to th |
|
Direct, human phrasing and clear enginee |
2026-04-13 |
| COMMIT |
0.00 |
Migrate indexing analysis utils to use SymbolicExpr/Symbolic |
|
Mostly technical details, domain-specifi |
2026-04-13 |
| COMMIT |
0.00 |
PR #40679: [xla:gpu] Remove wait_on_operation_queues field |
|
Technical with issue references and conc |
2026-04-13 |
| COMMIT |
0.00 |
[XLA:GPU] Use scratch buffer in one-shot RA2A. |
|
Short, human technical commit with no AI |
2026-04-13 |
| COMMIT |
0.00 |
Early sharding conversion in `HandleAllReduce` which was any |
|
Informal tone with technical context, li |
2026-04-13 |
| COMMIT |
0.00 |
Remove deprecated mlir::AffineExpr overloads from RangeEvalu |
|
Technical and concise, no AI hallmarks. |
2026-04-13 |
| COMMIT |
0.00 |
[XLA:GPU] Add scratch memory management for GPU collectives |
|
Direct and technical with no AI indicato |
2026-04-13 |
| COMMIT |
0.00 |
[NFC] Delete platform specific TSL casts libraries (part 1). |
|
Concise, domain-specific commit, no sign |
2026-04-13 |
| COMMIT |
0.00 |
Automated Code Change |
|
Generic automated change message; no AI |
2026-04-13 |
| COMMIT |
0.00 |
Automated Code Change |
|
Generic automated change message; no AI |
2026-04-13 |
| COMMIT |
0.00 |
[XLA] Provide a default unimplemented implementation for `Sy |
|
Direct, terse, domain-specific phrasing. |
2026-04-13 |
| COMMIT |
0.00 |
[XLA:GPU] Integrate TritonXLAConvertUnsupportedTypesPass int |
|
Straightforward technical changelog with |
2026-04-13 |
| COMMIT |
0.00 |
PR #40502: [ROCm] Fix Group-gemm e2e tests to meet gfx950 hi |
|
Includes domain detail, typos, and infor |
2026-04-13 |
| COMMIT |
0.00 |
[XLA:GPU] Add nozapfhahn tags to tests that time out in cove |
|
Direct, domain-specific description; no |
2026-04-13 |
| PR |
0.00 |
Use Hermetic Python from rules_ml_toolchain |
|
— |
2026-04-03 |
| PR |
0.00 |
Add prefetch to testTakeWithRestartedWorker. |
|
— |
2026-04-14 |
| PR |
0.00 |
Add simplification for XorOp. Simplification covers canonica |
|
— |
2026-04-08 |
| PR |
0.00 |
Add VLOG to concatenate_dataset_op. |
|
— |
2026-04-14 |
| PR |
0.00 |
Edit evaluator to allow a specific custom call |
|
— |
2026-04-14 |
| PR |
0.00 |
Internal build change |
|
— |
2026-04-14 |
| PR |
0.00 |
Allow configuration of the `num_warmup_batch_threads` BatchF |
|
— |
2026-04-13 |
| PR |
0.00 |
Fork Converter functions into LiteRT to remove TF dependenci |
|
— |
2026-04-14 |
| PR |
0.00 |
Add minimal XLA test to validate CuTe DSL FFI registration |
|
— |
2026-04-14 |
| PR |
0.00 |
Update constant_op library from eager to lazy importing. |
|
— |
2026-04-14 |
| PR |
0.00 |
This change introduces a GetFD method to the SubProcess clas |
|
— |
2026-04-13 |
| PR |
0.00 |
Update ops cond library from eager to lazy importing. |
|
— |
2026-04-09 |
| PR |
0.00 |
Update eager monitoring library from eager to lazy importing |
|
— |
2026-04-14 |
| PR |
0.00 |
Fix delegate lifetime issue in tests. |
|
— |
2026-04-14 |
| PR |
0.00 |
Update eager execute library from eager to lazy importing. |
|
— |
2026-04-14 |
| PR |
0.00 |
Support input coloring for sync copy and slice uses. |
|
— |
2026-04-02 |
| PR |
0.00 |
Add axis count check in Mean op. |
|
— |
2026-04-14 |
| PR |
0.00 |
Update dtypes library from eager to lazy importing. |
|
— |
2026-04-14 |
| PR |
0.00 |
port EmitSliceToDynamicLLVMIR to produce KernelDefinition |
|
— |
2026-04-14 |
| PR |
0.00 |
Update tensor_conversion_registry library from eager to lazy |
|
— |
2026-04-09 |
| PR |
0.00 |
Update ops library from eager to lazy importing. |
|
— |
2026-04-09 |
| PR |
0.00 |
Add a new flag `xla_dump_hlo_to_subfolder` to `DebugOptions` |
|
— |
2026-04-14 |
| PR |
0.00 |
This makes DumpPerModuleProtobufToFile, DumpPerExecutionProt |
|
— |
2026-04-14 |
| PR |
0.00 |
PR #40585: Cross Host Data Transfers: Unify Prepared{Send,Re |
|
— |
2026-04-14 |
| PR |
0.00 |
In `ReadFileToString`, allow files to report length longer t |
|
— |
2026-04-14 |
| PR |
0.00 |
[XLA][HLO Value Tracking] Refactor a utility funtion |
|
— |
2026-04-03 |
| PR |
0.00 |
[xla:python] Auto-generate .pyis for native Python extension |
|
— |
2026-04-14 |
| PR |
0.00 |
port EmitPadToStaticLLVMIR to produce KernelDefinition |
|
— |
2026-04-13 |
| PR |
0.00 |
PR #40334: Add descriptor destructor callback to CopyToRemot |
|
— |
2026-04-14 |
| PR |
0.00 |
PR #40903: [xla:gpu] Correctly merge attributes from combine |
|
— |
2026-04-14 |
| PR |
0.00 |
Fix signed integer overflow in safe_scalar_binary_pow_op |
|
— |
2026-04-14 |
| PR |
0.00 |
Update XLA TPU to support async collectives, partially. |
|
— |
2026-04-14 |
| PR |
0.00 |
Fix out-of-bounds access and stack overflow in XLA parsing. |
|
— |
2026-04-13 |
| PR |
0.00 |
Refactor the FuseFullyConnectedAndMul optimization pass to r |
|
— |
2026-04-14 |
| PR |
0.00 |
port EmitRngGetAndUpdateStateLLVMIR to produce KernelDefinit |
|
— |
2026-04-10 |
| PR |
0.00 |
Fix failure of nnapi_delegate_test.cc due to float rounding. |
|
— |
2026-04-14 |
| PR |
0.00 |
Internal build change. |
|
— |
2026-04-13 |
| PR |
0.00 |
[XLA:GPU] Introduce strong type for tiled dimension IDs and |
|
— |
2026-04-14 |
| PR |
0.00 |
Default users of GetTfrtGpuClient(options) to |
|
— |
2026-04-09 |
| PR |
0.00 |
[XLA:CPU] Add FAST_COMPILE tests to CI. |
|
— |
2026-04-14 |
| PR |
0.00 |
Integrate LLVM at llvm/llvm-project@2cf353b5e856 |
|
— |
2026-04-13 |
| PR |
0.00 |
493236662 cuda 13 |
|
Minimal title; lacks any AI stylistic ha |
2026-04-14 |
| PR |
0.00 |
Refactor `SpmdPartitioner::ConvertUnreducedSubgroup` to use |
|
— |
2026-04-13 |
| PR |
0.00 |
PR #40763: [XLA:GPU] Migrate EmptyCmd to AsyncDoneThunk impl |
|
— |
2026-04-14 |
| PR |
0.00 |
Remove integer overflow issue in DivUp; replace usages in gp |
|
— |
2026-04-09 |
| PR |
0.00 |
[XLA] Add instruction hoist pass for bitcast and gte |
|
— |
2026-04-14 |
| PR |
0.00 |
[XLA] Adding pattern to collective pipeliner that allows to |
|
— |
2026-04-14 |
| PR |
0.00 |
[XLA:GPU][NFCI] cleanups after removing nested fusions |
|
— |
2026-04-10 |
| PR |
0.00 |
[PjRt-IFRT] Check that just one serialized_descriptor is pas |
|
— |
2026-04-10 |
| PR |
0.00 |
[XLA:CPU] Cap simplification pipeline fixed-point iterations |
|
— |
2026-04-14 |
| PR |
0.00 |
Check for coordination service incarnation mismatches. |
|
— |
2026-04-14 |
| PR |
0.00 |
make sort emitter async |
|
— |
2026-04-13 |
| PR |
0.00 |
Add c-api for PjRtDeviceEventRef. |
|
— |
2026-04-09 |
| PR |
0.00 |
Introducing option to control the number of window prefetche |
|
— |
2026-04-08 |
| PR |
0.00 |
Remove last uses of AddConstraints and FromTensorSize Affine |
|
— |
2026-04-09 |
| PR |
0.00 |
Remove deprecated AffineMap-based constructors and methods f |
|
— |
2026-04-09 |
| PR |
0.00 |
Migrate last constructors from indexing_map_serialization |
|
— |
2026-04-09 |
| PR |
0.00 |
[XLA:GPU] do not create regions for reduce arguments |
|
— |
2026-04-13 |
| PR |
0.00 |
Move SafeEvaluateSymbolicExpr to symbolic_expr.h |
|
— |
2026-04-13 |
| PR |
0.00 |
Remove IndexingMap::GetAffineMap() and all cache-related log |
|
— |
2026-04-07 |
| PR |
0.00 |
Use constexpr `absl::string_view` instead of `char` as per g |
|
— |
2026-04-13 |
| PR |
0.00 |
Add internal visibility |
|
— |
2026-04-14 |
| PR |
0.00 |
Fix cache miss handling in the XNNPack weight cache. |
|
— |
2026-04-14 |
| PR |
0.00 |
[XLA:GPU] Updated reshape tile propagation to support `kColl |
|
— |
2026-04-10 |
| PR |
0.00 |
[XLA] Make sure that executable serialization is determinist |
|
— |
2026-04-09 |
| PR |
0.00 |
PR #40684: [XLA:GPU] Migrate LaunchCmd to its correspondi |
|
— |
2026-04-14 |
| PR |
0.00 |
[XLA:GPU] Retire xla_gpu_experimental_enable_split_k_rewrite |
|
— |
2026-04-14 |
| PR |
0.00 |
Remove unused dependencies on tsl/platform:types |
|
— |
2026-04-13 |
| PR |
0.00 |
Convert unreduced and manual shardings in the format picker, |
|
— |
2026-04-09 |
| PR |
0.00 |
[XLA:GPU] Update default Triton autotuner configs for B200. |
|
— |
2026-04-14 |
| PR |
0.00 |
PR #40656: [GPU] Wire deadlock prevention for async collecti |
|
— |
2026-04-14 |
| PR |
0.00 |
[XLA:GPU] Remove range_mapped option from multicast memory r |
|
— |
2026-04-14 |
| PR |
0.00 |
Fix b200/h100 tests since lib/Dialect/Triton/IR/Types.cpp ch |
|
— |
2026-04-14 |
| PR |
0.00 |
Optimize MultiOutputFusion reachability updates. |
|
— |
2026-04-14 |
| PR |
0.00 |
Move gemm fusion's IsSupportedTritonInstruction over to the |
|
— |
2026-03-12 |
| PR |
0.00 |
[XLA:GPU] Add a debug option to force a specific split_k val |
|
— |
2026-04-14 |
| PR |
0.00 |
Migrate remaining codegen users to use IndexingMap::Symbolic |
|
— |
2026-04-09 |
| PR |
0.00 |
PR #40460: Refactor Triton_XLA atomic operations lowering (E |
|
— |
2026-04-14 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-12 |
| PR |
0.00 |
[Autotuner] Improve logging for configs skipped due to compi |
|
— |
2026-04-14 |
| PR |
0.00 |
[XLA:GPU] Emit bitcast with the new tiling. |
|
— |
2026-04-13 |
| PR |
0.00 |
PR #40878: [stream_executor] Fix DCHECK in CommandBufferTh |
|
— |
2026-04-14 |
| PR |
0.00 |
Migrate and remove IndexingMap::ConstraintsSatisfied(AffineE |
|
— |
2026-04-08 |
| PR |
0.00 |
[XLA:GPU] Simple list scheduler to produce concurrent comman |
|
— |
2026-04-14 |
| PR |
0.00 |
Regenerate warnings file. |
|
— |
2026-04-14 |
| PR |
0.00 |
Reword error message in XNNPack delegate weight cache. |
|
— |
2026-04-14 |
| PR |
0.00 |
PR #40847: [ROCm] Fix LoadKernel to use refcounted module pa |
|
— |
2026-04-14 |
| PR |
0.00 |
PR #40239: Fix DWYU in xla/service/gpu/BUILD |
|
— |
2026-04-07 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-14 |
| PR |
0.00 |
PR #40838: Canonicalize custom element sizes on tuple leaf a |
|
— |
2026-04-14 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-14 |
| PR |
0.00 |
PR #40849: [xla:gpu] Remove unused IsNestedCommandBuffer API |
|
— |
2026-04-14 |
| PR |
0.00 |
Improve BroadcastCanonicalizer to create a transpose for the |
|
— |
2026-04-10 |
| PR |
0.00 |
PR #35304: [XLA:GPU] [plugin] Adding sycl/oneapi plugin supp |
|
— |
2026-04-14 |
| PR |
0.00 |
PR #40684: [XLA:GPU] Migrate LaunchCmd to its correspondi |
|
— |
2026-04-13 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-12 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-14 |
| PR |
0.00 |
[XLA:PJRT] Align collective memory with respect to library s |
|
— |
2026-04-13 |
| PR |
0.00 |
[XLA:GPU] Remove deprecated usages of SynchronousMemZero. |
|
— |
2026-04-13 |
