yang.tian

Get the same case from my side. @franklei01 You mean by set below env macro to 1 before run llama-cli would get vulkan output correctly? GGML_VK_DISABLE_COOPMAT

> > Get the same case from my side. > > [@franklei01](https://github.com/franklei01) You mean by set below env macro to 1 before run llama-cli would get vulkan output correctly? GGML_VK_DISABLE_COOPMAT...

`root@localhost:~/build-vulkan/bin# taskset -c 0,5,6,7,8,9,10,11 ./llama-bench -m Qwen2.5-3B-Instruct-Q4_0.gguf -pg 128,128 -t 8 ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = Mali-G720-Immortalis (Mali-G720-Immortalis) | uma: 1 | fp16: 1 | warp size:...

meet the same issue building armnn 22.11.01 using gcc12.3

> 建 tmp 文件的话，后续推理正确么？看着每次都没有缓存 Update cache to tmp/mnn_cachefile.bin, size = 3015836 Open tmp/mnn_cachefile.bin error Write Cache File error! 这个文件是否存在貌似对性能有比较大的影响？ 我这边测试的时候vulkan上看到prefill差异很大

> > > 建 tmp 文件的话，后续推理正确么？看着每次都没有缓存 > > > > > > Update cache to tmp/mnn_cachefile.bin, size = 3015836 Open tmp/mnn_cachefile.bin error Write Cache File error! > > 这个文件是否存在貌似对性能有比较大的影响？ 我这边测试的时候vulkan上看到prefill差异很大...