Geri Peterson comments

Results 31 comments of


                                            Geri Peterson

add test checking ns/pods for annotations allowing/preferring management cores

/retest-required

Disable internalTrafficPolicy=Local service tests for cilium

> what the purpose of this CI job is, since it's hard to say whether disabling the test is appropriate or not without knowing why the job is being run...

add test checking ns/pods for annotations allowing/preferring management cores

/retest-required

add test checking ns/pods for annotations allowing/preferring management cores

/retest-required

add test checking ns/pods for annotations allowing/preferring management cores

/retest-required

add test checking ns/pods for annotations allowing/preferring management cores

Deprecating this in favor of https://github.com/openshift/origin/pull/27770

Segfaults when running examples using GPU inside a VM

`system_profiler SPDisplaysDataType` doesn't report anything. Running llama.cpp with MPS support compiled in, it reports this: ``` ggml_metal_init: allocating ggml_metal_init: found device: Apple Paravirtual device ggml_metal_init: picking default device: Apple Paravirtual...

Segfaults when running examples using GPU inside a VM

Yes, it's a VM running on a M2 Pro.

Segfaults when running examples using GPU inside a VM

I've confirmed that argumentBuffersSupport is reporting 0 in my MacOS VM.

Segfaults when running examples using GPU inside a VM

> if llama.cpp works I wouldn't say that llama.cpp works - it detects the paravirtualized GPU, but it reports errors when attempting to offload any layers onto the GPU.