dbl
dbl
``` % ./clinfo Number of platforms 1 Platform Name Apple Platform Vendor Apple Platform Version OpenCL 1.2 (Dec 16 2022 20:35:20) Platform Profile FULL_PROFILE Platform Extensions cl_APPLE_SetMemObjectDestructor cl_APPLE_ContextLoggingFunctions cl_APPLE_clut cl_APPLE_query_kernel_names...
The issue is resolved. Thanks!
Any ideas? ``` $ conda update conda Solving environment: done ==> WARNING: A newer version of conda exists. 4.5.4-py27_0 conda-build: 1.21.3-py27_0 --> 3.10.5-py27_0 conda-forge setuptools: 27.2.0-py27_0 --> 39.2.0-py27_0 conda-forge Proceed...
Does this solve the problem(s): $ conda update -q conda --clobber > On Jul 4, 2018, at 1:19 AM, sarajcev wrote: > > I have the same issue with conda...
My iMac 27" running MacOS 14.6 with an AMD Radeon Pro 5700 XT, MTLCreateSystemDefaultDevice() returning nil. Any idea why MTLCreateSystemDefaultDevice() returns nil? The AMD GPU works with Pytorch MPS and...
@akaraon8bit Thanks for your response. Same error with you branch. ``` % cmake .. -DGGML_METAL=ON -- The C compiler identification is AppleClang 15.0.0.15000309 -- The CXX compiler identification is AppleClang...
``` % ./bin//llama-cli -m ~/llama.cpp-orig/models/7B/ggml-model-q4_0-v2.gguf -n 256 --repeat_penalty 1.0 --color -i -r "User:" --main-gpu 0 warning: llama.cpp was compiled without CUDA/SYCL/Vulkan. Setting the main GPU has no effect. Log start...
What happens on your Mac if you compile, link and run my test.m? ``` #import #import #import #import static id createCustomMTLDevice(void) { NSArray *devices = MTLCopyAllDevices(); for (id dev in...
MTLCreateSystemDefaultDevice() was always returning nil. (I'm still not sure why.) Before: ``` id device = MTLCreateSystemDefaultDevice(); with ``` After: ``` < static id createCustomMTLDevice(void) { NSArray *devices = MTLCopyAllDevices(); for...
``` $ conda install -c conda-forge umap-learn Collecting package metadata (current_repodata.json): done Solving environment: done ## Package Plan ## environment location: /Users/davidlaxer/anaconda/envs/lda2vec added / updated specs: - umap-learn The following...