Skip to content

Actions: CodeLinaro/executorch

Actions

MLX

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
mlx.yml
116 workflow runs
116 workflow runs

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
Support extra quantizable ops in advance quant above def chain (#21757) MLX #116: Commit a1eee71 pushed by qti-horodnic
19s main
main
19s
Fix XNNPACK rejecting avg_pool2d with default arguments (#21862) MLX #115: Commit 9ffbe36 pushed by qti-horodnic
33s main
main
33s
Reseed the Cortex-M test RNG before each test module is imported (#21… MLX #114: Commit 3253a28 pushed by qti-horodnic
27s main
main
27s
Share selective prim-ops helper (#21732) MLX #113: Commit 7857dfd pushed by chenweng-quic
18s main
main
18s
Qualcomm AI Engine Direct - Add QNN HadamardTransform op support (#21… MLX #112: Commit 43f89fb pushed by qti-horodnic
31s main
main
31s
Arm backend: Fix pad transpose handling around grid sampler (#21738) MLX #111: Commit c56e6bf pushed by qti-horodnic
15s main
main
15s
Qualcomm AI Engine Direct - Update quant recipe for PyTorch version b… MLX #110: Commit 5a77b43 pushed by shewu-quic
23s main
main
23s
Infer XNNPACK conv dimensionality from the weight rank (#21588) MLX #109: Commit 9cd0c12 pushed by qti-horodnic
34s main
main
34s
Optimize CUDA export host memory usage (#21617) MLX #108: Commit a439afd pushed by qti-horodnic
34s main
main
34s
Adjust how nax are excluded on < macOS 26.0 (#21554) MLX #107: Commit b4ffdbe pushed by qti-horodnic
20s main
main
20s
Add end-to-end sampling controls to the LLM server worker protocol (#… MLX #106: Commit 454f979 pushed by qti-horodnic
18s main
main
18s
[MLX] Add off-graph KV cache ring runtime (#21532) MLX #105: Commit 6bbb75a pushed by qti-horodnic
38s main
main
38s
Fix DS-CNN Cortex-M input memory format (#21485) MLX #104: Commit d632341 pushed by qti-horodnic
19s main
main
19s
[executorch][devtools] Reset profiler state in ETDump tests MLX #103: Commit a1d4d35 pushed by qti-horodnic
16s main
main
16s
Revert "[xnnpack] Support bf16 delegation for fully-connected (#21409)" MLX #102: Commit a886f38 pushed by qti-horodnic
16s main
main
16s
Qualcomm AI Engine Direct - Adding QNN backend support for the sort c… MLX #101: Commit d0fe35d pushed by shewu-quic
39s main
main
39s
Qualcomm AI Engine Direct - Test Framework Refactor #2 (#20735) MLX #100: Commit 8001512 pushed by qti-horodnic
24s main
main
24s
merge fbcode-only TARGETS rules into existing targets.bzl files (#21145) MLX #99: Commit ff0f92e pushed by qti-horodnic
15s main
main
15s
Qualcomm AI Engine Direct - [GenAI Pipeline] PR2: Strategy Interfaces… MLX #98: Commit 53551c1 pushed by qti-horodnic
17s main
main
17s
Arm backend: Add DeepSeek-R1-Distill-Qwen FP8 layer tests (#21012) MLX #97: Commit e8c47d7 pushed by qti-horodnic
50s main
main
50s
Add channel-wise gated delta rule custom op (#20913) MLX #96: Commit 931ba24 pushed by qti-horodnic
16s main
main
16s
Remove unused using-declarations (#20953) MLX #95: Commit 96c83ed pushed by qti-horodnic
17s main
main
17s
Prevent packed weight cache file from growing on reload (#20833) MLX #94: Commit be9b80c pushed by qti-horodnic
16s main
main
16s
MLX Q5K/Q6K upgrades (#20827) MLX #93: Commit a6d812a pushed by chenweng-quic
19s main
main
19s
Mlx improve 6bit packing perf (#20806) MLX #92: Commit f4b01a8 pushed by qti-horodnic
16s main
main
16s