When using the qwen2.5-vl model on AMD Ryzen APU under Windows, the error "failed to allocate Vulkan0 buffer of size 4342230552" may appear.

[xeden3]

Name and Version

C:\Users\xeden\Downloads\llama-b5255-bin-win-vulkan-x64>llama-cli --version
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = AMD Radeon(TM) 8060S Graphics (AMD proprietary driver) | uma: 1 | fp16: 1 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
version: 5255 (d24d592)
built with MSVC 19.43.34808.0 for x64

Operating systems

Windows

GGML backends

Vulkan

Hardware

CPU AMD Ryzen AI MAX 395 Memory 128G （CPU 64G GPU 64G）

Models

Qwen2.5-VL-3B-Instruct-f16.gguf

Problem description & steps to reproduce

Device
CPU AMD Ryzen AI MAX 395
Memory
128GB GPU 64mb, CPU 64mb
Operating system
win11
Used llama.cpp version
llama-b5255-bin-win-vulkan-x64

Since AMD does not support ROCM of Ryzen AI MAX 395, I used vulkan as the backends, and it is no problem to run most of the llm models, including deepseek.

First Bad Commit

No response

Relevant log output

C:\Users\xeden\Downloads\llama-b5255-bin-win-vulkan-x64>llama-mtmd-cli -m Qwen2.5-VL-3B-Instruct-f16.gguf --mmproj mmproj-Qwen2.5-VL-3B-Instruct-f16.gguf -p '描述图片内容.' --image demo.jpg
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = AMD Radeon(TM) 8060S Graphics (AMD proprietary driver) | uma: 1 | fp16: 1 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
build: 5255 (d24d5928) with MSVC 19.43.34808.0 for x64
llama_model_load_from_file_impl: using device Vulkan0 (AMD Radeon(TM) 8060S Graphics) - 65536 MiB free
llama_model_loader: loaded meta data with 27 key-value pairs and 434 tensors from Qwen2.5-VL-3B-Instruct-f16.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = qwen2vl
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen2.5 VL 3B Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Qwen2.5-VL
llama_model_loader: - kv   5:                         general.size_label str              = 3B
llama_model_loader: - kv   6:                        qwen2vl.block_count u32              = 36
llama_model_loader: - kv   7:                     qwen2vl.context_length u32              = 128000
llama_model_loader: - kv   8:                   qwen2vl.embedding_length u32              = 2048
llama_model_loader: - kv   9:                qwen2vl.feed_forward_length u32              = 11008
llama_model_loader: - kv  10:               qwen2vl.attention.head_count u32              = 16
llama_model_loader: - kv  11:            qwen2vl.attention.head_count_kv u32              = 2
llama_model_loader: - kv  12:                     qwen2vl.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  13:   qwen2vl.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  14:                          general.file_type u32              = 1
llama_model_loader: - kv  15:            qwen2vl.rope.dimension_sections arr[i32,4]       = [16, 24, 24, 0]
llama_model_loader: - kv  16:               general.quantization_version u32              = 2
llama_model_loader: - kv  17:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  18:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  19:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  20:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  21:                      tokenizer.ggml.merges arr[str,151387]  = ["臓 臓", "臓臓 臓臓", "i n", "臓 t",...
llama_model_loader: - kv  22:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  23:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  24:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  25:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  26:                    tokenizer.chat_template str              = {% set image_count = namespace(value=...
llama_model_loader: - type  f32:  181 tensors
llama_model_loader: - type  f16:  253 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = F16
print_info: file size   = 5.75 GiB (16.00 BPW)
load: special tokens cache size = 22
load: token to piece cache size = 0.9310 MB
print_info: arch             = qwen2vl
print_info: vocab_only       = 0
print_info: n_ctx_train      = 128000
print_info: n_embd           = 2048
print_info: n_layer          = 36
print_info: n_head           = 16
print_info: n_head_kv        = 2
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: n_swa_pattern    = 1
print_info: n_embd_head_k    = 128
print_info: n_embd_head_v    = 128
print_info: n_gqa            = 8
print_info: n_embd_k_gqa     = 256
print_info: n_embd_v_gqa     = 256
print_info: f_norm_eps       = 0.0e+00
print_info: f_norm_rms_eps   = 1.0e-06
print_info: f_clamp_kqv      = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale    = 0.0e+00
print_info: f_attn_scale     = 0.0e+00
print_info: n_ff             = 11008
print_info: n_expert         = 0
print_info: n_expert_used    = 0
print_info: causal attn      = 1
print_info: pooling type     = 0
print_info: rope type        = 8
print_info: rope scaling     = linear
print_info: freq_base_train  = 1000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 128000
print_info: rope_finetuned   = unknown
print_info: ssm_d_conv       = 0
print_info: ssm_d_inner      = 0
print_info: ssm_d_state      = 0
print_info: ssm_dt_rank      = 0
print_info: ssm_dt_b_c_rms   = 0
print_info: model type       = 3B
print_info: model params     = 3.09 B
print_info: general.name     = Qwen2.5 VL 3B Instruct
print_info: vocab type       = BPE
print_info: n_vocab          = 151936
print_info: n_merges         = 151387
print_info: BOS token        = 151643 '<|endoftext|>'
print_info: EOS token        = 151645 '<|im_end|>'
print_info: EOT token        = 151645 '<|im_end|>'
print_info: PAD token        = 151643 '<|endoftext|>'
print_info: LF token         = 198 '膴'
print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
print_info: FIM MID token    = 151660 '<|fim_middle|>'
print_info: FIM PAD token    = 151662 '<|fim_pad|>'
print_info: FIM REP token    = 151663 '<|repo_name|>'
print_info: FIM SEP token    = 151664 '<|file_sep|>'
print_info: EOG token        = 151643 '<|endoftext|>'
print_info: EOG token        = 151645 '<|im_end|>'
print_info: EOG token        = 151662 '<|fim_pad|>'
print_info: EOG token        = 151663 '<|repo_name|>'
print_info: EOG token        = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 0 repeating layers to GPU
load_tensors: offloaded 0/37 layers to GPU
load_tensors:   CPU_Mapped model buffer size =  5886.42 MiB
...........................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 4096
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch       = 2048
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 1
llama_context: flash_attn    = 0
llama_context: freq_base     = 1000000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (128000) -- the full capacity of the model will not be utilized
llama_context:        CPU  output buffer size =     0.58 MiB
init: kv_size = 4096, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 36, can_shift = 1
init:        CPU KV buffer size =   144.00 MiB
llama_context: KV self size  =  144.00 MiB, K (f16):   72.00 MiB, V (f16):   72.00 MiB
llama_context:    Vulkan0 compute buffer size =   941.25 MiB
llama_context: Vulkan_Host compute buffer size =    12.01 MiB
llama_context: graph nodes  = 1338
llama_context: graph splits = 508 (with bs=512), 1 (with bs=1)
common_init_from_params: setting dry_penalty_last_n to ctx_size = 4096
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
mtmd_cli_context: chat template example:
<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
Hello<|im_end|>
<|im_start|>assistant
Hi there<|im_end|>
<|im_start|>user
How are you?<|im_end|>
<|im_start|>assistant

clip_ctx: CLIP using Vulkan0 backend
clip_model_loader: model name:   Qwen2.5 VL 3B Instruct
clip_model_loader: description:
clip_model_loader: GGUF version: 3
clip_model_loader: alignment:    32
clip_model_loader: n_tensors:    519
clip_model_loader: n_kv:         22

load_hparams: projector:          qwen2.5vl_merger
load_hparams: has_llava_proj:     0
load_hparams: minicpmv_version:   0
load_hparams: proj_scale_factor:  0
load_hparams: n_wa_pattern:       8
load_hparams: use_silu:           1
load_hparams: use_gelu:           0
load_hparams: model size:         1276.39 MiB
load_hparams: metadata size:      0.18 MiB
alloc_compute_meta:    Vulkan0 compute buffer size =   208.69 MiB
alloc_compute_meta:        CPU compute buffer size =    13.38 MiB
main: Qwen2.5-VL-3B-Instruct-f16.gguf
encoding image or slice...
ggml_vulkan: Device memory allocation of size 4342230552 failed.
ggml_vulkan: Requested buffer size exceeds device memory allocation limit: ErrorOutOfDeviceMemory
ggml_gallocr_reserve_n: failed to allocate Vulkan0 buffer of size 4342230552
D:\a\llama.cpp\llama.cpp\ggml\src\ggml-backend.cpp:1663: GGML_ASSERT((char *)addr + ggml_backend_buffer_get_alloc_size(buffer, tensor) <= (char *)ggml_backend_buffer_get_base(buffer) + ggml_backend_buffer_get_size(buffer)) failed

[xeden3]

It fix at b5359