Bug: win-vulkan-x64 crashed since b3831

[cwt]

What happened?

Since the rebar (#9251) merged in b3831, loading to AMD RX 580 on Windows via Vulkan crashed.
FYI:

• My mainboard (Z97-HD3) does not support rebar.
• Releases before b3831 work fine.

Name and Version

❯ .\llama-cli.exe --version
version: 3831 (89f99449)
built with MSVC 19.29.30154.0 for x64

What operating system are you seeing the problem on?

Windows

Relevant log output

ggml_vulkan: Found 1 Vulkan devices:
Vulkan0: Radeon RX 580 Series (AMD proprietary driver) | uma: 0 | fp16: 0 | warp size: 64
llm_load_tensors: ggml ctx size =    0.27 MiB
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 33/33 layers to GPU
llm_load_tensors: Radeon RX 580 Series buffer size =  4095.05 MiB
llm_load_tensors:        CPU buffer size =    70.31 MiB
..............................................................................................
llama_new_context_with_model: n_ctx      = 2048
llama_new_context_with_model: n_batch    = 2048
llama_new_context_with_model: n_ubatch   = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base  = 10000.0
llama_new_context_with_model: freq_scale = 1
ggml_vulkan: Device memory allocation of size 268435456 failed.
ggml_vulkan: vk::Device::allocateMemory: ErrorOutOfDeviceMemory
llama_kv_cache_init: failed to allocate buffer for kv cache
llama_new_context_with_model: llama_kv_cache_init() failed for self-attention cache
llama_init_from_gpt_params: failed to create context with model '..\westlake-7b-v2.Q4_K_M.gguf'
main: error: unable to load model

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale.