| COMMIT |
0.20 |
Automated Code Change |
|
'Automated Code Change' is generic; poss |
2026-04-02 |
| PR |
0.10 |
Fix softmax kernel to zero out invalid channels in output |
|
Direct bug explanation, concise with spe |
2026-01-14 |
| PR |
0.10 |
Fix int16x8 quantization for SQRT op in TFLite |
|
Free-text is highly technical and matche |
2026-04-03 |
| PR |
0.10 |
Fix int16x8 quantization for SQRT op in TFLite |
|
Repeated, technical explanation, no AI l |
2026-04-03 |
| PR |
0.10 |
Fix XLA compilation failure for tf.random.shuffle (compariso |
|
Detailed technical fix, uses XLA and Ten |
2026-04-03 |
| PR |
0.10 |
Fix tf.math.polyval to match numpy.polyval for single-coeffi |
|
Bug report reference, domain-specific wi |
2026-03-10 |
| COMMIT |
0.00 |
[XLA] Put BufferAssignment dumps on a diet |
|
Informal, domain-specific summary and co |
2026-04-03 |
| COMMIT |
0.00 |
Populate xla_input_shapes for unpacked inputs in IfrtServing |
|
Brief, technical commit with no AI hallm |
2026-04-03 |
| COMMIT |
0.00 |
feat: Add StructuredMetric to tensorflow request cost. |
|
Standard technical commit, no sign of AI |
2026-04-03 |
| COMMIT |
0.00 |
Automated Code Change |
|
Standard 'Automated Code Change' label, |
2026-04-03 |
| COMMIT |
0.00 |
Automated Code Change |
|
Standard 'Automated Code Change' label, |
2026-04-03 |
| COMMIT |
0.00 |
Automated Code Change |
|
Standard 'Automated Code Change' label, |
2026-04-03 |
| COMMIT |
0.00 |
Internal build change. |
|
Generic commit message, typical for inte |
2026-04-03 |
| COMMIT |
0.00 |
Enable TpuHostAllocator for IFRT in TfrtSession. |
|
Technical commit, domain-specific with n |
2026-04-03 |
| COMMIT |
0.00 |
2. add FunctionalHloRunner::CompileAndRun overload to accept |
|
Technical wording, no signs of AI-genera |
2026-04-03 |
| COMMIT |
0.00 |
Added a bounds check to FastParseExample |
|
Typical developer commit, no signs of AI |
2026-04-03 |
| COMMIT |
0.00 |
Reverts 6875c44fbadab26295dd9839963ab1311c0215cf |
|
Terse, direct revert with code reference |
2026-04-03 |
| COMMIT |
0.00 |
Automated Code Change |
|
Standard automated commit message; style |
2026-04-03 |
| COMMIT |
0.00 |
Automated Code Change |
|
Standard auto-generated infra commit mes |
2026-04-03 |
| COMMIT |
0.00 |
[IFRT IR] Do not run Shardy roundtrip export pipeline before |
|
Technical, domain-specific; no AI-style |
2026-04-03 |
| COMMIT |
0.00 |
PR #40329: [xla:gpu] Cleanup execution stream id in GPU runt |
|
Technical detail, PR template, and direc |
2026-04-03 |
| COMMIT |
0.00 |
Add a test for `Array::ByteSize()` |
|
Brief, domain-specific test addition; co |
2026-04-03 |
| COMMIT |
0.00 |
Don't assign group_id to counter line(s). |
|
Short, informal fix note; matches typica |
2026-04-03 |
| COMMIT |
0.00 |
Integrate LLVM at llvm/llvm-project@7ccd92e5e6e5 |
|
Template-based, technical content, no AI |
2026-04-02 |
| COMMIT |
0.00 |
Erase async collectives in XLA CPU. |
|
Long, but technical, thorough, and with |
2026-04-02 |
| COMMIT |
0.00 |
[IFRT] Add `Value::ByteSize` method |
|
Technical, structured API explanation; r |
2026-04-02 |
| COMMIT |
0.00 |
[IFRT IR] Do not apply identity IfrtArraType conversion in l |
|
Short, technical commit with domain term |
2026-04-02 |
| COMMIT |
0.00 |
Remove unused reset logic from coordination agent. |
|
Brief, domain-specific commit typical fo |
2026-04-02 |
| COMMIT |
0.00 |
[XLA:CPU] Rename is_fusion_emitters to use_fusion_emitters f |
|
Concise technical message, domain-specif |
2026-04-02 |
| COMMIT |
0.00 |
Migrate multithreaded_compilation_test to PjRt runtime. |
|
Technical changelog, domain-specific, no |
2026-04-02 |
| COMMIT |
0.00 |
[tsl] Clean up #includes in errors.h and status.h |
|
Terse, uses abbreviations, concise goal |
2026-04-02 |
| COMMIT |
0.00 |
[XLA] Wrap loops containing only DCHECKs with ifndef NDEBUG. |
|
Domain-specific, terse, no AI markers. |
2026-04-02 |
| COMMIT |
0.00 |
Use salted hashing for key_hash so that we have fewer collis |
|
Informal, specific benchmarks, no AI phr |
2026-04-02 |
| COMMIT |
0.00 |
[XLA:CPU] Add Opt Preset FAST_COMPILE for interactive and te |
|
Changelog style, has domain specifics, n |
2026-04-02 |
| COMMIT |
0.00 |
Run `MakeArraysFromHostBuffer` and `CopyToHostBuffer` tests |
|
Direct, references concrete tests, clear |
2026-04-02 |
| COMMIT |
0.00 |
[IFRT IR] Add compile option to set strict memory reservatio |
|
Concise technical addition, no AI stylis |
2026-04-02 |
| COMMIT |
0.00 |
[XLA:CPU] Add Pi approximation to fusion microbenchmark. |
|
Direct technical language, context-rich, |
2026-04-02 |
| COMMIT |
0.00 |
Implement non-descending layout support in `CpuRawBuffer::Co |
|
Bug fix explained clearly, technical, no |
2026-04-02 |
| COMMIT |
0.00 |
Centralize PjRt Transpose Caching in CommonPjRtClient. |
|
Technical description, bulleted updates, |
2026-04-02 |
| COMMIT |
0.00 |
Drop deduplicating any calls on outliner. |
|
Technical jargon and concise, informal t |
2026-04-02 |
| COMMIT |
0.00 |
PR #40117: Update XLA oneAPI presubmit build targets |
|
Detailed, domain-specific PR with some f |
2026-04-02 |
| COMMIT |
0.00 |
Populate device_memory_bytes_limit attribute while reconstru |
|
Domain-specific content and phrasing; co |
2026-04-02 |
| COMMIT |
0.00 |
Reverts e6f36bd7a12f87aac6f21a5068719dfc91bed3eb |
|
Single-purpose revert message; standard |
2026-04-02 |
| COMMIT |
0.00 |
Remove unneeded condition variable from coordination service |
|
Terse, domain-specific commit message. |
2026-04-02 |
| COMMIT |
0.00 |
Make `HloProgram::name()` return a unique and stable name ev |
|
Technical and specific wording; informal |
2026-04-02 |
| COMMIT |
0.00 |
Rollback of PR #39854 |
|
Standard rollback message, typical commi |
2026-04-02 |
| COMMIT |
0.00 |
Original change is causing presubmit tests failure. Rolling |
|
Human rationale and informal explanation |
2026-04-02 |
| COMMIT |
0.00 |
HLO builder tuple_test is hardware-independent. |
|
Technical explanation with human-written |
2026-04-02 |
| COMMIT |
0.00 |
Reverts cd712c81dacec1d737af7e27dc01c8fc0a7f5020 |
|
Standard auto-generated revert message f |
2026-04-02 |
| COMMIT |
0.00 |
Consolidate sanitizer build checks for tfrt_session_python_t |
|
Terse, domain-specific commit. Likely hu |
2026-04-02 |
| COMMIT |
0.00 |
PR #40311: [xla:gpu] Delete vestigial WaitForStreamsThunk |
|
Domain jargon, imports, no AI markers. |
2026-04-02 |
| COMMIT |
0.00 |
Make XLA:GPU propagate all CPU HW features to FFI and XLA:CP |
|
Somewhat formal but uses technical detai |
2026-04-02 |
| COMMIT |
0.00 |
[mpmd] Use reserved_hbm_bytes attribute to reserve per-fragm |
|
Template style, technical context, not A |
2026-04-02 |
| COMMIT |
0.00 |
Bump rules_python 1.8.4 -> 1.8.5 to restore correct URL-base |
|
Specific technical context, informal and |
2026-04-02 |
| COMMIT |
0.00 |
Add TargetMachineOptions::Native() to create options for the |
|
Technical vocabulary, tests, not AI-like |
2026-04-02 |
| COMMIT |
0.00 |
[XLA:GPU] Do not run large HLO fusions concurrently in comma |
|
Short, technical, no AI text signals. |
2026-04-02 |
| COMMIT |
0.00 |
[XLA:GPU] Use XLA_VLOG_DEVICE where device id is useful in l |
|
Terse, log context, fits human commit. |
2026-04-02 |
| COMMIT |
0.00 |
Stabilize SymbolicExpr and SymbolicMap string representation |
|
CL note, details concise, domain-specifi |
2026-04-02 |
| COMMIT |
0.00 |
PR #39373: [ROCm] Fix issue with unsupported types combinati |
|
Uses PR template; free-text sections are |
2026-04-02 |
| COMMIT |
0.00 |
Automated Code Change |
|
Standard auto-generated commit; no AI ha |
2026-04-02 |
| COMMIT |
0.00 |
PR #40232: Add missing kAllGatherStart/kAllGatherDone verifi |
|
Template-driven; free-text is concise an |
2026-04-02 |
| COMMIT |
0.00 |
Migrate indexing analysis from MLIR Affine to SymbolicMap |
|
Technical, domain-specific, no AI-style |
2026-04-02 |
| COMMIT |
0.00 |
Remove unused `options` parameter from `CompileTargetBinary` |
|
Concise commit, clear changelog, no AI-w |
2026-04-02 |
| COMMIT |
0.00 |
Remove test timeout long from prng_test. |
|
Very brief, informal, and specific commi |
2026-04-02 |
| COMMIT |
0.00 |
[XLA:GPU] Accumulate TiledHloInstructions for the runtime va |
|
Domain-specific vocabulary, informal exp |
2026-04-02 |
| COMMIT |
0.00 |
[XLA:GPU] Introduce EmitterContext to group the params. |
|
Short, technical title; lacks AI writing |
2026-04-02 |
| COMMIT |
0.00 |
Avoid crashing in HloVerifier for unexpected shapes in AllGa |
|
Bugfix commit, informal language without |
2026-04-02 |
| COMMIT |
0.00 |
PR #40252: [xla:gpu] Use Global HangWatchdog in se_gpu_pjrt_ |
|
PR summary is short, direct, and technic |
2026-04-02 |
| COMMIT |
0.00 |
[NFC] Annotate forwarding headers with `INLINER_FORWARD_TO`. |
|
Technical and concise; normal engineerin |
2026-04-02 |
| COMMIT |
0.00 |
Make CpuTargetMachineOptions always available through GpuTop |
|
Human-written, clear summary, no AI sign |
2026-04-02 |
| COMMIT |
0.00 |
Migrate XLA codegen attributes and operations to the new Sym |
|
Contains domain-specific terminology and |
2026-04-02 |
| COMMIT |
0.00 |
[XLA:GPU] Normalize two batch dimensions (which may appear a |
|
Human style, includes jargon and straigh |
2026-04-02 |
| COMMIT |
0.00 |
Roll-forward Migrate XLA GPU emitters and HWIR to use Symbol |
|
Direct, technical, and detailed—no AI ha |
2026-04-02 |
| COMMIT |
0.00 |
PR #39951: [xla:gpu] Add missing scheduling for all-gather-s |
|
Mostly template import text plus concise |
2026-04-02 |
| COMMIT |
0.00 |
Improve parentheses in SymbolicExpr serialization |
|
Simple, informal explanation with minima |
2026-04-02 |
| COMMIT |
0.00 |
PR #39843: Bump jwalton/gh-find-current-pr from 1.3.3 to 1.3 |
|
— |
2026-04-02 |
| COMMIT |
0.00 |
PR #39622: [ROCm] Use BFCAllocator for scratch allocations n |
|
Slightly formal, but includes typos and |
2026-04-02 |
| COMMIT |
0.00 |
[XLA:GPU] Add symmetric memory to collective memory cache to |
|
Technical, informal, and uses in-domain |
2026-04-02 |
| COMMIT |
0.00 |
Always pass TargetMachineOptions to FFI calls from CustomCal |
|
Precise engineering note, no AI text ind |
2026-04-02 |
| COMMIT |
0.00 |
Automated Code Change |
|
Generic automated commit, no AI signals, |
2026-04-02 |
| COMMIT |
0.00 |
Automated Code Change |
|
Generic automated commit, no AI signals, |
2026-04-02 |
| COMMIT |
0.00 |
Update rules_ml_toolchain to the version with Hermetic Pytho |
|
Human-like brief update description, cle |
2026-04-02 |
| COMMIT |
0.00 |
[IFRT] Add more general `Layout::ByteSize` static methods |
|
Technical, detailed, domain‑jargon prese |
2026-04-02 |
| COMMIT |
0.00 |
[IFRT] Add GetName() method to HloProgram |
|
Issue-only commit, concise, no markers o |
2026-04-02 |
| COMMIT |
0.00 |
Fix heap-use-after-free in ConstraintPropagator::PropagateCo |
|
Domain-specific explanation, informal, n |
2026-04-02 |
| COMMIT |
0.00 |
Remove condition hints that are based on future's readiness |
|
Concise and technical rationale, informa |
2026-04-02 |
| COMMIT |
0.00 |
Mark coordination service movable but not copyable. |
|
Short, technical, lacks structure common |
2026-04-01 |
| COMMIT |
0.00 |
[GPU] Use CheckFabricHomogeneity in RaggedAllToAllThunk |
|
Technical, structured, uses domain terms |
2026-04-01 |
| COMMIT |
0.00 |
Reverts f6b594dc036bed5a4d59ee60e69698e8219501b2 |
|
Standard revert message, common human ph |
2026-04-01 |
| COMMIT |
0.00 |
[ReplicaGroupV3][Refactor][18/n] migrate more XLA functions |
|
Terse, technical, commit-style message w |
2026-04-01 |
| COMMIT |
0.00 |
[XLA] Relax memory ordering of `entry->next` access in `~Obj |
|
Technical writeup, natural phrasing, ref |
2026-04-01 |
| COMMIT |
0.00 |
Remove `allow_new_incarnation_to_reconnect` config from coor |
|
Brief removal message; no AI signals, do |
2026-04-01 |
| COMMIT |
0.00 |
Make an explicit ref type for PjRtDeviceEvent to allow easil |
|
Specific technical intent, colloquial wo |
2026-04-01 |
| COMMIT |
0.00 |
[ReplicaGroupV3][Refactor][17/n] migrate functions in spmd/ |
|
Refactor message, technical context, ter |
2026-04-01 |
| COMMIT |
0.00 |
Add PID metadata to XPlanes and TraceMeConsumers to enable p |
|
Describes technical change in one clear |
2026-04-01 |
| COMMIT |
0.00 |
[XLA] Make `ObjectPool::Entry::next` atomic |
|
Short, domain-specific commit; no AI-lik |
2026-04-01 |
| COMMIT |
0.00 |
Benchmark for traceme_encode. |
|
Minimal benchmark addition, no AI langua |
2026-04-01 |
| COMMIT |
0.00 |
[tfrt] Introduce DeviceInterconnectResource to bridge Global |
|
Contains some structure, but detailed te |
2026-04-01 |
| COMMIT |
0.00 |
Update Shardy to the latest commit. |
|
Routine update, minimal content, highly |
2026-04-01 |
| COMMIT |
0.00 |
[XLA] Remove obsolete shmap & sdy manual computation inliner |
|
Technical commit message with revert and |
2026-04-01 |
| COMMIT |
0.00 |
Grant users of XLA access to gpu_topology_util |
|
Brief, jargon-heavy message; no AI phras |
2026-04-01 |
| COMMIT |
0.00 |
Add a test for `jit(lambda x: x, out_shardings=unreduced)` a |
|
Concise, uses jargon and code refs, read |
2026-04-01 |
| COMMIT |
0.00 |
Internal visibility change. |
|
Extremely terse and generic; typical hum |
2026-04-01 |
| COMMIT |
0.00 |
Drop fully deduplicating on outliner and leave it to unflatt |
|
Uses domain-specific concepts; informal |
2026-04-01 |
| COMMIT |
0.00 |
Add SymbolicExpr::ReplaceDims(absl::Span |
|
Technical addition; notes requirement, n |
2026-04-01 |
| PR |
0.00 |
Reverts 5975d605381857588fc5c05c68c10c2a8f230413 |
|
— |
2026-04-03 |
| PR |
0.00 |
Recursively clean up some unused TSL dependencies |
|
— |
2026-04-02 |
| PR |
0.00 |
Added an assert in hlo_verifier for bitcast on memory space |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Add HostMemoryAllocator extension and implement GetHostMemor |
|
— |
2026-04-03 |
| PR |
0.00 |
Integrate StableHLO at openxla/stablehlo@05fdca09 |
|
— |
2026-03-30 |
| PR |
0.00 |
[XLA] Put BufferAssignment dumps on a diet |
|
— |
2026-03-28 |
| PR |
0.00 |
1. Enable offloading bf16 reductions to ynnpack |
|
— |
2026-04-02 |
| PR |
0.00 |
Populate xla_input_shapes for unpacked inputs in IfrtServing |
|
— |
2026-03-26 |
| PR |
0.00 |
feat: Add StructuredMetric to tensorflow request cost. |
|
— |
2026-04-03 |
| PR |
0.00 |
Do not fail on host compiler on serving. |
|
— |
2026-04-03 |
| PR |
0.00 |
Use Hermetic Python from rules_ml_toolchain |
|
— |
2026-04-03 |
| PR |
0.00 |
PR #40376: [xla:gpu] TraceMe for while loop iterations |
|
— |
2026-04-03 |
| PR |
0.00 |
Enable native TPU profiling with XProf with libkineto integr |
|
— |
2026-04-02 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Simplify CommitChunk method |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
PR #40331: [XLA:GPU][oneAPI] Fix build failure in IntelGpuCo |
|
— |
2026-04-03 |
| PR |
0.00 |
[XLA][HLO Value Tracking] Refactor a utility funtion |
|
— |
2026-04-03 |
| PR |
0.00 |
Internal build change. |
|
— |
2026-04-02 |
| PR |
0.00 |
[XLA:GPU] remove nested gemm fusion code |
|
— |
2026-03-23 |
| PR |
0.00 |
[StableHLO reference] Add support for broadcast/dot in inter |
|
— |
2026-04-02 |
| PR |
0.00 |
Enable TpuHostAllocator for IFRT in TfrtSession. |
|
— |
2026-04-03 |
| PR |
0.00 |
PR #39201: [xla:gpu] Split legacy custom calls into LegacyCu |
|
— |
2026-04-03 |
| PR |
0.00 |
This is a test |
|
— |
2026-04-03 |
| PR |
0.00 |
Rename WatchJobState to WatchTasks in coordination service. |
|
— |
2026-04-03 |
| PR |
0.00 |
2. add FunctionalHloRunner::CompileAndRun overload to accept |
|
— |
2026-04-03 |
| PR |
0.00 |
Added a bounds check to FastParseExample |
|
— |
2026-04-02 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-03-27 |
| PR |
0.00 |
[XLA:CPU] Add Opt Preset FAST_COMPILE for interactive and te |
|
— |
2026-04-03 |
| PR |
0.00 |
Add `NamedSharding` support to `GatherScatterOperandsSharded |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Reverts 6875c44fbadab26295dd9839963ab1311c0215cf |
|
— |
2026-04-03 |
| PR |
0.00 |
Not printing the extra attributes of async_wrapped_instructi |
|
— |
2026-04-02 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Integrate LLVM at llvm/llvm-project@c329cc59d91b |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Integrate LLVM at llvm/llvm-project@293623ce99d4 |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-02 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-02 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
[IFRT IR] Do not run Shardy roundtrip export pipeline before |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
[XLA] Re-land :Remove obsolete shmap & sdy manual computatio |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
Automated Code Change |
|
— |
2026-04-03 |
| PR |
0.00 |
PR #40329: [xla:gpu] Cleanup execution stream id in GPU runt |
|
— |
2026-04-02 |
| PR |
0.00 |
Add a test for `Array::ByteSize()` |
|
— |
2026-04-03 |
| PR |
0.00 |
Don't assign group_id to counter line(s). |
|
— |
2026-04-03 |
| PR |
0.00 |
Always clear custom allocation in subgraph cache before resi |
|
— |
2026-04-03 |
| PR |
0.00 |
Fix HostOffloader kSelect layout mismatch crashes and simpli |
|
— |
2026-04-03 |
| PR |
0.00 |
introduce KernelCompiler interface |
|
— |
2026-04-02 |
| PR |
0.00 |
Refactor vhlo::TensorV1Attr to store DenseElementsAttr |
|
— |
2026-03-23 |
| PR |
0.00 |
Integrate LLVM at llvm/llvm-project@7ccd92e5e6e5 |
|
— |
2026-03-31 |
| PR |
0.00 |
Erase async collectives in XLA CPU. |
|
— |
2026-04-01 |
| PR |
0.00 |
[IFRT] Add `Value::ByteSize` method |
|
— |
2026-04-01 |
| PR |
0.00 |
[IFRT IR] Do not apply identity IfrtArraType conversion in l |
|
— |
2026-03-31 |
| PR |
0.00 |
[IFRT IR] Do not apply identity IfrtArraType conversion in l |
|
— |
2026-04-02 |
| PR |
0.00 |
Remove unused reset logic from coordination agent. |
|
— |
2026-04-02 |
| PR |
0.00 |
Serialize peak buffers to fix 100% fragmentation metrics on |
|
— |
2026-04-02 |
| PR |
0.00 |
[XLA:CPU] Rename is_fusion_emitters to use_fusion_emitters f |
|
— |
2026-04-02 |
