Jaroslav Sevcik 735f4bb631 PR #32905: Allow mixed precision operands for async collective permute ... Imported from GitHub PR https://github.com/openxla/xla/pull/32905 📝 Summary of Changes Allow mixed precision asynchronous collective-permute in the verifier. 🎯 Justification Fixes https://github.com/openxla/xla/issues/32845 🚀 Kind of Contribution 🐛 Bug Fix 📊 Benchmark (for Performance Improvements) N/A 🧪 Unit Tests: Tests that verifier passes on mixed precision collective-permute-start and collective-permute-done. 🧪 Execution Tests: Manually testes the JAX repro from https://github.com/openxla/xla/issues/32845 Copybara import of the project: -- f44faa7ce7ecfbd810983cae170a118bb19a8bb3 by Jaroslav Sevcik <jsevcik@nvidia.com>: Allow mixed precision operands for async collective permute Merging this change closes #32905 PiperOrigin-RevId: 822023349		2025-10-21 03:22:25 -07:00
..
android
boringssl
cpuinfo
fft2d
flatbuffers	Update from flatbuffers 25.2.10 to 25.9.23.	2025-10-01 16:25:25 -07:00
googleapis
hexagon
icu
jpeg
kissfft
libprotobuf_mutator
libwebp
mpi
opencl_headers
pasta
py	Fix incorrect python interpreter path of non-bzlmod	2025-10-14 08:36:47 -07:00
pybind11_protobuf
ruy
sobol_data
systemlibs
tf_runtime	Update TFRT dependency to use revision	2025-09-04 12:02:07 -07:00
vulkan_headers
xla	PR #32905: Allow mixed precision operands for async collective permute	2025-10-21 03:22:25 -07:00
xprof	[TSL] Clean up integral types	2025-10-17 14:19:08 -07:00
__init__.py
arm_neon_2_x86_sse.BUILD
BUILD.bazel
codegen.BUILD
coremltools.BUILD
cub.BUILD
gif_fix_image_counter.patch
gif_fix_strtok_r.patch
gif.BUILD
linenoise.BUILD
nlohmann_json.BUILD
png_fix_rpi.patch
png.BUILD
pprof.BUILD
repo.bzl	Simplify tf_vendored repo rule.	2025-10-02 00:42:00 -07:00
sqlite.BUILD
tf_toolchains.BUILD
tflite_mobilenet_float.BUILD
tflite_mobilenet_quant.BUILD
tflite_mobilenet.BUILD
tflite_ovic_testdata.BUILD
tflite_smartreply.BUILD