- 8513e5f Resolving binding references when applying deferred command buffers. (#17840) by Ben Vanik · 9 months ago
- dcc8a0d Retaining binding tables in HIP/CUDA action queues. (#17839) by Ben Vanik · 9 months ago
- f8f2996 Retaining binding tables and plumbing indirect cmds in local-task. (#17838) by Ben Vanik · 9 months ago
- 0c90e5e Fixing Metal build break. by Ben Vanik · 9 months ago
- d2895c2 Actually implement bytecode verifier IREE_VM_VERIFY_REG_ANY. (#17829) by Ben Vanik · 9 months ago
- 9ffe473 Making HAL command buffers take buffers as indirect args. (#17730) by Ben Vanik · 9 months ago
- 96c9bfb Optimizing queries for optional VM functions. (#17823) by Ben Vanik · 9 months ago
- 129878f Generalizing task system queuing and supporting callbacks. (#17820) by Ben Vanik · 9 months ago
- 68b00aa Fixing task system worker tracy utilization plot on exit. (#17821) by Ben Vanik · 9 months ago
- 13e6b7e Removing nested command buffers and adding indirect execution. (#17724) by Ben Vanik · 9 months ago
- 1070f05 [Riscv] Implement a empty cpu initialize function for generic-riscv_64 (#17750) by Yun Hsiang · 9 months ago
- 895f40a Fixing use of non-standard i64 literal suffix on Windows. by Ben Vanik · 9 months ago
- 450db0c Change `EncodingRole` to `IntegerAttr` (#17708) by lialan · 9 months ago
- ac418d1 Integrate llvm/llvm-project@27ac46e6bea2 (#17662) by Lei Zhang · 9 months ago
- 1ea21d1 Fix hip dynamic_symbols_test to check min version. (#17674) by Scott Todd · 9 months ago
- c5d4b96 Allow flags to be set with greater flexibility (#17659) by Dave Liddell · 10 months ago
- 6d9475e Fixing iree_vm_ref_wrap_retain. (#17610) by Ben Vanik · 10 months ago
- 5404ad7 Add versioned, automatically installed 'buildifier' pre-commit hook. (#17589) by Scott Todd · 10 months ago
- 9a33952 [cuda][hip] Fix a resource leak when using deferred command buffers. (#17582) by Andrew Woloszyn · 10 months ago
- 65bbc4b Update internal time library to allow user defined now function (#17576) by CindyLiu · 10 months ago
- 50a0669 Work around circular dependency in tracing/console.c. (#17493) by Scott Todd · 10 months ago
- 6d4eea6 Add missing test guards (#17540) by Maksim Levental · 10 months ago
- e876020 Strided pack/unpack ukernels (#17516) by Benoit Jacob · 10 months ago
- 62efaee Format files across the project using pre-commit. (#17534) by Scott Todd · 10 months ago
- d47f86e [hip][rocm] Switch to use old hipDeviceProp_t for queries (#17522) by Lei Zhang · 10 months ago
- 117cb43 Test 'console' provider in 'tracing' job. (#16454) by Scott Todd · 10 months ago
- 9e3d27a Upgrade to nanobind 2.0. (#17497) by Stella Laurenzo · 10 months ago
- 3d6a8ee Bump Tracy to https://github.com/wolfpld/tracy/commit/cf2344111. (#17488) by Scott Todd · 10 months ago
- 3a2617f [runtime][hip][cuda] Fix semaphore multi-wait, action GPU events and cleanup (#17213) by Boian Petkantchin · 10 months ago
- ea7d01e Pin nanobind to 1.9.2 to defer 2.0.0 API changes. (#17481) by Scott Todd · 10 months ago
- d4aa849 [CPU] Add support for pack/unpack ukernels enablement on llvm-cpu path. (#17427) by Han-Chung Wang · 10 months ago
- 9f59514 Add AVX-512 pack ukernel tile function for `16x2xbf16`. (#17432) by Benoit Jacob · 10 months ago
- 4132d2e [runtime][hal][hip] Implement collectives via RCCL (#17270) by Boian Petkantchin · 10 months ago
- 218b934 Support GGUF version 2 as well as 3. (#17319) by Scott Todd · 10 months ago
- b4fc0b4 Implementing the f64 VM extension and flipping the flag by default. (#17416) by Ben Vanik · 10 months ago
- b716704 Update git-clang-format ref and clang-format version. (#16792) by Scott Todd · 10 months ago
- d18c5d8 [vulkan] Print VkResult as int32 value in errors (#17362) by Lei Zhang · 11 months ago
- d8d9b8e [hip] Use PRIhsz for iree_host_size_t values (#17360) by Lei Zhang · 11 months ago
- 0b8b13c Converting some runtime benchmarks to use our C API. (#17336) by Ben Vanik · 11 months ago
- 9406b9c [runtime] Fix buffer diagnostics compiler errors (#17325) by Benjamin Maxwell · 11 months ago
- 3ca0a49 Moving OutlineConstantsPass to flow and adding parameter support. (#17303) by Ben Vanik · 11 months ago
- 098b0c4 Add test_amd_mi250 CI job including ROCm matmul tests. (#17293) by erman-gurses · 11 months ago
- 71a9945 Adding `--iree-opt-import-parameters=` and cleaning up export. (#16828) by Ben Vanik · 11 months ago
- b8ef25c Fixing threading test reported by TSAN. (#17260) by Ben Vanik · 11 months ago
- e2bdf9c [runtime][vulkan][cts] Disable flaky test WaitForFiniteTime on Android (#17246) by Boian Petkantchin · 11 months ago
- e4b5a93 [runtime][hal][cts] Add test to wait on all semaphores on multiple places simultaneously (#17240) by Boian Petkantchin · 11 months ago
- e088c0b [python] Adds DLPack import and export support for BufferView. (#17131) by Stella Laurenzo · 11 months ago
- 5fa2480 [runtime][cts] add test where a batch is waiting on a smaller value than signaled (#17141) by Boian Petkantchin · 11 months ago
- 729ebc6 [runtime][metal] exclude properly the failing semaphore test (#17151) by Boian Petkantchin · 11 months ago
- 30acc53 [runtime][cts] add test where a device batch signals another and the host (#17138) by Boian Petkantchin · 11 months ago
- 290d812 [runtime][cts] add semaphore test where a batch waits on another and a host signal (#17130) by Boian Petkantchin · 11 months ago
- 568bb31 [runtime][cts] Add test waiting on a semaphore for finite time and fix Vulkan driver (#17126) by Boian Petkantchin · 11 months ago
- 655b71a Executable library call hooks system, and a sample Linux/CPU event implementation (#15803) by Benoit Jacob · 11 months ago
- 36b3ce1 [runtime][cts] Add test to wait multiple times for the same semaphore value (#17125) by Boian Petkantchin · 11 months ago
- 44ccc22 [runtime][hip][cuda] Fix bug where zombified actions may not get cleaned up (#17107) by Boian Petkantchin · 11 months ago
- f4bee0c [runtime] Make the runtime more TSan-friendly (#17051) by Boian Petkantchin · 11 months ago
- 0f6bc24 [runtime][hip][cuda] Fix mutex locking when waiting on a semaphore (#17118) by Boian Petkantchin · 11 months ago
- 78005ef [runtime][cts] add test where 2 batches wait on different semaphore values (#17091) by Boian Petkantchin · 11 months ago
- 074cbf3 [runtime] Refactor semaphore submission CTS (#17108) by Boian Petkantchin · 11 months ago
- 3f51a55 Replace openxla/iree with iree-org/iree across the project. (#17110) by Scott Todd · 11 months ago
- a2476ce [metal] Disable failing semaphore submission test until fixing (#17100) by Lei Zhang · 11 months ago
- 3677fbc [runtime] Add semaphore test where 2 batches wait on a former batch amongst 2 (#17080) by Boian Petkantchin · 11 months ago
- cd282de [runtime][hip][cuda] Fix waiting on a semaphore on the host (#17073) by Boian Petkantchin · 11 months ago
- 459fab6 [runtime][hip][cuda] Fix waiting on wait semaphores before executing actions (#17025) by Boian Petkantchin · 12 months ago
- 1c49d6a [runtime][hip][cuda] Add tracing in graph execution mode (#16894) by Boian Petkantchin · 12 months ago
- 40f2533 [HIP] Add inline execution mode (#16951) by Nithin Meganathan · 12 months ago
- fbd31b0 [Vulkan] Fix coop matrix property initialization (#17023) by Jakub Kuderski · 12 months ago
- 2780fd5 Fix typo in benchmark tracing warning message. by Ben Vanik · 12 months ago
- 5d2af54 [python] Convert python io tests to unit tests. (#16984) by Stella Laurenzo · 12 months ago
- 5ad0fe2 [python] Add missing public alias of symbol. (#16980) by Stella Laurenzo · 12 months ago
- 27670b6 Bump nanobind version in more requirement files. (#16976) by Scott Todd · 12 months ago
- 11d2259 Fix arm and windows builder issues at head. by Stella Laurenzo · 12 months ago
- 4f40080 [python] Flesh out more of the python parameters API. (#16957) by Stella Laurenzo · 12 months ago
- be9f097 [hip] Introduce options to control load of libamdhip64.so. (#16766) by Stella Laurenzo · 12 months ago
- c46daa6 Fix for iree-run-module with --input=not-a-path.bin (#16919) by James Newling · 12 months ago
- daee1dd Ukernels: replace boilerplate by tables. (#16879) by Benoit Jacob · 12 months ago
- 2cdf145 fix build errors when tracing mode = 1 (#16884) by Okwan Kwon · 1 year ago
- 5f2743b [hip] Move into hal/drivers and build by default (#16706) by Lei Zhang · 1 year ago
- 767a611 [tracing] fix build errors when tracing mode = 1 (#16853) by Okwan Kwon · 1 year ago
- e7eef08 Adds a nullptr check around optional implementation in dynamic modules. (#16845) by Stella Laurenzo · 1 year ago
- 77cc34b Bump numpy dep up to the 2.0 prerelease. (#16800) by Scott Todd · 1 year ago
- 2eae9b3 [CPU] Remove 8x8x16 i8mm microkernel by mariecwhite · 1 year ago
- 92fe572 [CPU] Add s8s4s32 i8mm ukernel (#16678) by mariecwhite · 1 year ago
- b61a918 Enable LTO optimization by default for runtime releases. (#16811) by Stella Laurenzo · 1 year ago
- 2395046 [rocm] Excises (almost) dependence on /opt/rocm from the compiler. (#16803) by Stella Laurenzo · 1 year ago
- d05b4a1 Splitting stack trace support out of status.c. (#16791) by Ben Vanik · 1 year ago
- 15d9039 Embedding executable source contents in binaries for tracing. (#16757) by Ben Vanik · 1 year ago
- e12ab47 Replace `unaryOperator` by EmitC LogicalNotOp (#16730) by Marius Brehler · 1 year ago
- e9f7ecd [cuda][hip] Drop name_literal reference like Vulkan side (#16742) by Lei Zhang · 1 year ago
- 27b837c Replace `binaryOperator` by EmitC ops (#16728) by Marius Brehler · 1 year, 1 month ago
- 7da8af6 Cleanup a few docs/references to old paths in HAL/Target. (#16716) by Scott Todd · 1 year, 1 month ago
- b5af996 Prefer broadcasting RHS over LHS in AVX-512 multiply-accumulate instructions (#16709) by Benoit Jacob · 1 year, 1 month ago
- f34e534 Replace k with m by mariecwhite · 1 year, 1 month ago
- 4d3c93f Add missing macros to dotprod ukernel by mariecwhite · 1 year, 1 month ago
- 8adae37 [cuda][hip] Add support for semaphore multi wait (#16638) by Lei Zhang · 1 year, 1 month ago
- 9d6d99f faster narrow mmt4d ukernels on x86 (#16655) by Benoit Jacob · 1 year, 1 month ago
- 4f1f055 mmt4d ukernel: use fewer magic macros to generate tile-functions M0-variants (#16645) by Benoit Jacob · 1 year, 1 month ago
- b994b72 Reenable accidentally disabled architecture-specific parts of `mmt4d_test` (#16654) by Benoit Jacob · 1 year, 1 month ago
- f433fd2 Using iree.abi.name consistently for arg/result names. (#16635) by Ben Vanik · 1 year, 1 month ago
- fe5e69a [cuda][hip] Shorten deferred queue worker name (#16642) by Lei Zhang · 1 year, 1 month ago