[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention #10474
Triggered via pull request
February 14, 2026 04:12
tianleiwu
Status
Success
Total duration
25m 31s
Artifacts
–
windows_x86.yml
on: pull_request
build_x86_release
23m 7s
Annotations
9 warnings
|
build_x86_release:
onnxruntime/test/autoep/library/example_plugin_ep/ep_arena.cc#L132
'=': conversion from 'const int64_t' to 'size_t', possible loss of data
|
|
|
|
|
|
|
|
|
|
build_x86_release:
onnxruntime/test/autoep/library/example_plugin_ep_kernel_registry/kernels/binary_op.cc#L94
'*=': conversion from '_Ty' to 'size_t', possible loss of data
|
|
build_x86_release:
onnxruntime/core/optimizer/nchwc_transformer.cc#L883
'~': zero extending 'size_t' to 'int64_t' of greater size
|
|
build_x86_release:
onnxruntime/core/optimizer/nchwc_transformer.cc#L381
'~': zero extending 'size_t' to 'int64_t' of greater size
|
|
build_x86_release:
onnxruntime/core/optimizer/nchwc_transformer.cc#L348
'~': zero extending 'size_t' to 'int64_t' of greater size
|