Failed to load the model Phi 4 on ROCm-runtime

[jurykor]

🥲 Failed to load the model

Error loading model.

(Exit code: 18446744072635812000). Unknown error. Try a different model and/or config.

Windows 11 Pro 24H2, 26100.2605
AMD Ryzen 7 7700 / 64Gb
AMD Radeon RX 7800 XT / 16Gb / AMD Software 24.12.1
LM Studio 0.3.6

With ROCm 1.1.10, 1.1.13 - "Error loading model"
With Vulkan - all ok

2025-01-10.1-rocm-1.10-err.log
2025-01-10.1-rocm-1.13-err.log
2025-01-10.1-vulkan-ok.log

[jurykor]

The model imported from 'ollama' loads normally:

Import:

ollama pull phi4:14b-q4_K_M
copy G:\AI\.ollama\blobs\sha256-fd7b6731c33c57f61767612f56517460ec2d1e2e5a3f0163e0eb3d8d8cb5df20 G:\AI\.lmstudio\models\_ollama\phi4\phi4-14b-q4_K_M.gguf 

Loading with ROCm 1.1.10:

[2025-01-11 15:56:20][DEBUG] AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | 

[2025-01-11 15:56:20][DEBUG] llama_model_loader: loaded meta data with 33 key-value pairs and 243 tensors from G:\AI\.lmstudio\models\_ollama\phi4\phi4-14b-q4_K_M.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              = phi3
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Phi 4
llama_model_loader: - kv   3:                            general.version str              = 4
llama_model_loader: - kv   4:                       general.organization str              = Microsoft
llama_model_loader: - kv   5:                           general.basename str              = phi
llama_model_loader: - kv   6:                         general.size_label str              = 15B
llama_model_loader: - kv   7:                            general.license str              = mit
llama_model_loader: - kv   8:                       general.license.link str              = https://huggingface.co/microsoft/phi-...
llama_model_loader: - kv   9:                               general.tags arr[str,7]       = ["phi", "nlp", "math", "code", "chat"...
llama_model_loader: - kv  10:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv  11:                        phi3.context_length u32              = 16384
llama_model_loader: - kv  12:  phi3.rope.scaling.original_context_length u32              = 16384
llama_model_loader: - kv  13:                      phi3.embedding_length u32              = 5120
llama_model_loader: - kv  14:                   phi3.feed_forward_length u32              = 17920
llama_model_loader: - kv  15:                           phi3.block_count u32              = 40
llama_model_loader: - kv  16:                  phi3.attention.head_count u32              = 40
llama_model_loader: - kv  17:               phi3.attention.head_count_kv u32              = 10
llama_model_loader: - kv  18:      phi3.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  19:                  phi3.rope.dimension_count u32              = 128
llama_model_loader: - kv  20:                        phi3.rope.freq_base f32              = 250000.000000
llama_model_loader: - kv  21:                          general.file_type u32              = 15

[2025-01-11 15:56:20][DEBUG] llama_model_loader: - kv  22:              phi3.attention.sliding_window u32              = 131072
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = dbrx

[2025-01-11 15:56:20][DEBUG] llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,100352]  = ["!", "\"", "#", "$", "%", "&", "'", ...

[2025-01-11 15:56:20][DEBUG] llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,100352]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...

[2025-01-11 15:56:20][DEBUG] llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,100000]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  28:                tokenizer.ggml.bos_token_id u32              = 100257
llama_model_loader: - kv  29:                tokenizer.ggml.eos_token_id u32              = 100257
llama_model_loader: - kv  30:            tokenizer.ggml.padding_token_id u32              = 100257
llama_model_loader: - kv  31:                    tokenizer.chat_template str              = {% for message in messages %}{% if (m...
llama_model_loader: - kv  32:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   81 tensors
llama_model_loader: - type q4_K:  101 tensors
llama_model_loader: - type q5_K:   40 tensors
llama_model_loader: - type q6_K:   21 tensors

[2025-01-11 15:56:20][DEBUG] llm_load_vocab: special tokens cache size = 96

[2025-01-11 15:56:20][DEBUG] llm_load_vocab: token to piece cache size = 0.6151 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = phi3
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 100352
llm_load_print_meta: n_merges         = 100000
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 16384
llm_load_print_meta: n_embd           = 5120
llm_load_print_meta: n_layer          = 40
llm_load_print_meta: n_head           = 40
llm_load_print_meta: n_head_kv        = 10
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_swa            = 131072
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 4

[2025-01-11 15:56:20][DEBUG] llm_load_print_meta: n_embd_k_gqa     = 1280
llm_load_print_meta: n_embd_v_gqa     = 1280
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 17920
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 2
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 250000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 16384
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: ssm_dt_b_c_rms   = 0
llm_load_print_meta: model type       = 14B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 14.66 B
llm_load_print_meta: model size       = 8.43 GiB (4.94 BPW) 
llm_load_print_meta: general.name     = Phi 4
llm_load_print_meta: BOS token        = 100257 '<|endoftext|>'
llm_load_print_meta: EOS token        = 100257 '<|endoftext|>'
llm_load_print_meta: PAD token        = 100257 '<|endoftext|>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOT token        = 100265 '<|im_end|>'
llm_load_print_meta: max token length = 256

[2025-01-11 15:56:21][DEBUG] ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
  Device 0: AMD Radeon RX 7800 XT, compute capability 11.0, VMM: no
llm_load_tensors: ggml ctx size =    0.26 MiB

[2025-01-11 15:56:25][DEBUG] llm_load_tensors: offloading 40 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 41/41 layers to GPU
llm_load_tensors:      ROCm0 buffer size =  8354.71 MiB
llm_load_tensors:        CPU buffer size =   275.62 MiB

[2025-01-11 15:56:28][DEBUG] llama_new_context_with_model: n_ctx      = 16384
llama_new_context_with_model: n_batch    = 512
llama_new_context_with_model: n_ubatch   = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base  = 250000.0
llama_new_context_with_model: freq_scale = 1

[2025-01-11 15:56:28][DEBUG] llama_kv_cache_init:      ROCm0 KV buffer size =  3200.00 MiB
llama_new_context_with_model: KV self size  = 3200.00 MiB, K (f16): 1600.00 MiB, V (f16): 1600.00 MiB

[2025-01-11 15:56:28][DEBUG] llama_new_context_with_model:  ROCm_Host  output buffer size =     0.38 MiB

[2025-01-11 15:56:28][DEBUG] llama_new_context_with_model:      ROCm0 compute buffer size =  1357.00 MiB
llama_new_context_with_model:  ROCm_Host compute buffer size =    42.01 MiB
llama_new_context_with_model: graph nodes  = 1606
llama_new_context_with_model: graph splits = 2