llama.cpp
vulkan: Fix ErrorOutOfHostMemory on Intel GPU when loading large models with --no-mmap
#20059

Merged

Commits

Changed to reuse command buffers to fix crashing on Intel GPU

rillomas committed 27 days ago
Removed unused parameter

rillomas committed 27 days ago
Fixed compile error and minor mistake

rillomas committed 26 days ago
Fix logging

rillomas committed 26 days ago
Changing to use usage flag per command buffer

rillomas committed 21 days ago
fixed style

rillomas committed 21 days ago
added buffer reset

rillomas committed 21 days ago
Removed cmd_buffer_idx for reuse consistency

rillomas committed 20 days ago
Merge remote-tracking branch 'origin/master' into fix-async-tensor-crash

rillomas committed 20 days ago
Fixed style

rillomas committed 20 days ago