PR #21160 Cross-backend profiler

Cross-backend profiler #21160

pwilkin wants to merge 8 commits into master from cross-profiler

github-actions added Nvidia GPU

github-actions added Vulkan

github-actions added examples

github-actions added python

github-actions added ggml

github-actions added SYCL

github-actions added Apple Metal

github-actions added Ascend NPU

github-actions added OpenCL

github-actions added IBM zDNN

github-actions added Hexagon

github-actions added OpenVINO

github-actions added WebGPU

github-actions added documentation

pwilkin force pushed from 532a8ebd to 1874fb9e 8 days ago

pwilkin force pushed from 1874fb9e to 0a20d658 6 days ago

github-actions added AMD ZenDNN

pwilkin force pushed from ec4489aa to d35b7668 6 days ago

github-actions added testing

pwilkin force pushed from d35b7668 to 65ab03a3 2 days ago

feat: cool profiler thingy

26459c7e

add second dimension to reported tensors, fix Mac build, add missing …

dee7edea

Fix more missing backend stuff (and Python errors)

92e45c8c

fix builds, integrate vulkan profiler, fix copy events, fix export

7baee997

fix mul_mat_id stats, add throughput stat, add envvar trigger, add co…

c293858e

docs, pass copy details

c907d259

Add missing op parameters to the profiler; add support for test-backe…

728f3654

Converge implementation with export-graph-ops

09cd7887

pwilkin force pushed from bd6f8008 to 09cd7887 1 day ago

Reviewers

No reviews

Assignees

No one assigned

Labels

documentation testing Nvidia GPU Vulkan examples python ggml SYCL Apple Metal Ascend NPU OpenCL IBM zDNN Hexagon AMD ZenDNN OpenVINO WebGPU

Milestone

No milestone

llama.cpp Cross-backend profiler #21160 Open

Cross-backend profiler #21160

llama.cpp
Cross-backend profiler
#21160

Open