Skip to content

Actions: ml-explore/mlx

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
2,500+ workflow runs
2,500+ workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
benchmarks: add Apple I8MM affine-QMM evidence harness Build and Test #3753: Pull request #4235 opened by PhilipJohnBasile
Action required PhilipJohnBasile:agent/mlx-highway-i8mm-20260813
PhilipJohnBasile:agent/mlx-highway-i8mm-20260813
Action required
[CUDA] Cholesky via cuSOLVER Build and Test #3752: Pull request #4208 synchronize by sashko-zakharchuk
Action required sashko-zakharchuk:cuda-cholesky
sashko-zakharchuk:cuda-cholesky
Action required
[CUDA][Improvement] RMSNorm backward (#3881) Build and Test #3751: Commit a8e24f2 pushed by nastya236
1h 51m 0s main
main
1h 51m 0s
Stabilize reduced-precision InstanceNorm Build and Test #3750: Pull request #4230 synchronize by ternaus
Action required ternaus:codex/instancenorm-fp16-stability
ternaus:codex/instancenorm-fp16-stability
Action required
Break monolithic MTLResidencySet into smaller sets (#4211) Build and Test #3749: Commit 09ebe73 pushed by zcbenz
1h 50m 38s main
main
1h 50m 38s
Add force_fused option to scaled_dot_product_attention Build and Test #3748: Pull request #4185 synchronize by zcbenz
1h 37m 31s hojin12312:force-fused-sdpa
hojin12312:force-fused-sdpa
1h 37m 31s
chore: Add runnable distributed examples (#4219) Build and Test #3747: Commit fd7f023 pushed by zcbenz
58m 45s main
main
58m 45s
chore: Validate decay_steps and step_size in the schedulers (#4217) Build and Test #3746: Commit c6ef1eb pushed by zcbenz
2m 19s main
main
2m 19s
Reuse Stockham twiddles in large batched Bluestein FFTs (#4084) Build and Test #3745: Commit d56ed24 pushed by zcbenz
27m 27s main
main
27m 27s
Break monolithic MTLResidencySet into smaller sets Build and Test #3743: Pull request #4211 synchronize by JamesMcCarthy44
50m 21s JamesMcCarthy44:feature/residency-sharding
JamesMcCarthy44:feature/residency-sharding
50m 21s
Stabilize reduced-precision InstanceNorm Build and Test #3742: Pull request #4230 opened by ternaus
Action required ternaus:codex/instancenorm-fp16-stability
ternaus:codex/instancenorm-fp16-stability
Action required
Fix Issue 4034 return as a tuple Build and Test #3741: Pull request #4229 synchronize by JasonHonKL
34m 46s JasonHonKL:issue/4034
JasonHonKL:issue/4034
34m 46s
Fix Issue 4034 return as a tuple Build and Test #3740: Pull request #4229 opened by JasonHonKL
Action required JasonHonKL:issue/4034
JasonHonKL:issue/4034
Action required
Fix the CPU scan over a size one axis with a padded stride Build and Test #3739: Pull request #4139 synchronize by kapellirohith
-1s kapellirohith:cpu-scan-size-one-axis
kapellirohith:cpu-scan-size-one-axis
-1s
Add force_fused option to scaled_dot_product_attention Build and Test #3738: Pull request #4185 synchronize by zcbenz
1h 27m 19s hojin12312:force-fused-sdpa
hojin12312:force-fused-sdpa
1h 27m 19s
Add force_fused option to scaled_dot_product_attention Build and Test #3737: Pull request #4185 synchronize by zcbenz
7m 12s hojin12312:force-fused-sdpa
hojin12312:force-fused-sdpa
7m 12s
Add force_fused option to scaled_dot_product_attention Build and Test #3736: Pull request #4185 synchronize by zcbenz
19m 19s hojin12312:force-fused-sdpa
hojin12312:force-fused-sdpa
19m 19s
Raise instead of hanging when reflect/symmetric pad gets an empty axi… Build and Test #3734: Commit 3f2e4a3 pushed by zcbenz
30m 27s main
main
30m 27s
Release build Release build #209: Scheduled
36m 32s main
main
36m 32s
Fix Metal sort for arrays with negative strides Build and Test #3733: Pull request #4226 synchronize by reckylurker
Action required reckylurker:fix/metal-sort-negative-strides
reckylurker:fix/metal-sort-negative-strides
Action required
Fix Metal sort for arrays with negative strides Build and Test #3732: Pull request #4226 opened by reckylurker
Action required reckylurker:fix/metal-sort-negative-strides
reckylurker:fix/metal-sort-negative-strides
Action required
fix(metal): preserve subnormal float values when casting to bool (#4205) Build and Test #3731: Pull request #4224 opened by reckylurker
25m 59s reckylurker:fix/metal-subnormal-bool-cast
reckylurker:fix/metal-subnormal-bool-cast
25m 59s
Optimize BF16 quantized matmul with FP16 tiles Build and Test #3730: Pull request #4216 synchronize by justinchuby
Action required justinchuby:optimize/bf16-qmm-fp16-tiles
justinchuby:optimize/bf16-qmm-fp16-tiles
Action required
Optimize BF16 quantized matmul with FP16 tiles Build and Test #3729: Pull request #4216 synchronize by justinchuby
Action required justinchuby:optimize/bf16-qmm-fp16-tiles
justinchuby:optimize/bf16-qmm-fp16-tiles
Action required
Raise instead of hanging when reflect/symmetric pad gets an empty axis Build and Test #3728: Pull request #4223 opened by codeAnqiang-ma
26m 11s codeAnqiang-ma:fix/pad-reflect-empty-axis
codeAnqiang-ma:fix/pad-reflect-empty-axis
26m 11s