Skip to content

Actions: KingDEV95/XNNPACK

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
714 workflow runs
714 workflow runs

Filter by Workflow

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Simplified fix for warnings in update-microkernels.py by recursively …
Build and update caches #999: Commit 46394a4 pushed by pull Bot
1d 0h 0m 3s master
Update KleidiAI in XNNPACK
Build and update caches #998: Commit d34f52c pushed by pull Bot
5h 59m 56s master
Don't allow broadcasts as the first dimension of dot inputs
Build and update caches #997: Commit d89bf2f pushed by pull Bot
18h 0m 6s master
Remove force_root from static_transpose scheduling
Build and update caches #996: Commit 23ba0fb pushed by pull Bot
5h 59m 59s master
Do not create serial loops for k2, k3, ...
Build and update caches #995: Commit 1eb7300 pushed by pull Bot
5h 59m 49s master
Merge pull request #10242 from ken-unger:f16-vlog-rvv
Build and update caches #994: Commit e2ab35a pushed by pull Bot
6h 0m 11s master
Add transcendental ops for every x86 architecture
Build and update caches #992: Commit d1da9a5 pushed by pull Bot
6h 0m 0s master
Remove RTTI from the Tensor API. Rework the Buffer hierarchy.
Build and update caches #991: Commit ac73c5b pushed by pull Bot
5h 59m 50s master
f16-vtanh using high-accuracy rational polynomial implementation.
Build and update caches #990: Commit 30e1a98 pushed by pull Bot
12h 0m 21s master
Replace rational polynomials for exp with non-rational polynomials
Build and update caches #988: Commit f8deca0 pushed by pull Bot
18h 0m 7s master
Add clarifying comments in call to define_transpose_a().
Build and update caches #987: Commit 2b99af3 pushed by pull Bot
18h 0m 0s master
Fix floor_log2(NaN) to be NaN
Build and update caches #986: Commit 894ae65 pushed by pull Bot
6h 0m 8s master
Fix precision issue in rndnu16 requantization for scales near powers …
Build and update caches #985: Commit fda3ca7 pushed by pull Bot
1d 0h 0m 4s master
Add math helpers to SIMD wrappers
Build and update caches #983: Commit cccad55 pushed by pull Bot
18h 0m 5s master
Remove unused transpose SIMD wrapper
Build and update caches #982: Commit 549deb8 pushed by pull Bot
6h 0m 0s master
gemm benchmark documentation fix
Build and update caches #981: Commit d4adfcd pushed by pull Bot
17h 59m 55s master
Merge pull request #10261 from velonica0:f16
Build and update caches #980: Commit b1a0a5d pushed by pull Bot
5h 59m 59s master
Properly open source tensor api in github through copybara
Build and update caches #979: Commit 5a59a54 pushed by pull Bot
18h 0m 8s master
Adjust bounds for elementwise unary kernels with sub-byte inputs.
Build and update caches #978: Commit ce14e18 pushed by pull Bot
6h 0m 14s master
Add xnn_datatype_qint2 for tensorwise quantized 2-bit values.
Build and update caches #977: Commit d0004f8 pushed by pull Bot
5h 59m 51s master
Split dot operation on K.
Build and update caches #976: Commit adf9795 pushed by pull Bot
6h 0m 10s master
Change tree reduction factor from 32 to 16, and add another level
Build and update caches #975: Commit 5191fee pushed by pull Bot
6h 0m 14s master