Bug: Phi3.5-mini-instruct Q4 K L gguf based llamafile CuDA error AMD iGPU

[eddan168]

Contact Details

What happened?

I made a llamafile with Phi-3.5-mini-instruct-Q4_K_L.gguf from HF but it runs out of memory with the default context window of 128K and limiting the context window to 2K runs into another failure. This is on Windows 11 with AMD Radeon 890M iGPU.

Version

llamafile v0.8.13

What operating system are you seeing the problem on?

Windows

Relevant log output

C:\llamafile>.\Phi-3.5-mini-instruct.llamafile -ngl 999 -c 2048
import_cuda_impl: initializing gpu module...
get_rocm_bin_path: note: amdclang++.exe not found on $PATH
get_rocm_bin_path: note: /C/Program Files/AMD/ROCm/6.1//bin/amdclang++.exe does not exist
get_rocm_bin_path: note: clang++.exe not found on $PATH
link_cuda_dso: note: dynamically linking /C/Users/eddan/.llamafile/v/0.8.13/ggml-rocm.dll
ggml_cuda_link: welcome to ROCm SDK with tinyBLAS
link_cuda_dso: GPU support loaded
{"build":1500,"commit":"a30b324","function":"server_cli","level":"INFO","line":2841,"msg":"build info","tid":"11681088","timestamp":1728583033}
{"function":"server_cli","level":"INFO","line":2844,"msg":"system info","n_threads":12,"n_threads_batch":-1,"system_info":"AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | ","tid":"11681088","timestamp":1728583033,"total_threads":24}
llama_model_loader: loaded meta data with 40 key-value pairs and 197 tensors from Phi-3.5-mini-instruct-Q4_K_L.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 3.5 Mini Instruct
llama_model_loader: - kv   3:                           general.finetune str              = instruct
llama_model_loader: - kv   4:                           general.basename str              = Phi-3.5
llama_model_loader: - kv   5:                         general.size_label str              = mini
llama_model_loader: - kv   6:                            general.license str              = mit
llama_model_loader: - kv   7:                       general.license.link str              = https://huggingface.co/microsoft/Phi-...
llama_model_loader: - kv   8:                               general.tags arr[str,3]       = ["nlp", "code", "text-generation"]
llama_model_loader: - kv   9:                          general.languages arr[str,1]       = ["multilingual"]
llama_model_loader: - kv  10:                        phi3.context_length u32              = 131072
llama_model_loader: - kv  11:  phi3.rope.scaling.original_context_length u32              = 4096
llama_model_loader: - kv  12:                      phi3.embedding_length u32              = 3072
llama_model_loader: - kv  13:                   phi3.feed_forward_length u32              = 8192
llama_model_loader: - kv  14:                           phi3.block_count u32              = 32
llama_model_loader: - kv  15:                  phi3.attention.head_count u32              = 32
llama_model_loader: - kv  16:               phi3.attention.head_count_kv u32              = 32
llama_model_loader: - kv  17:      phi3.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  18:                  phi3.rope.dimension_count u32              = 96
llama_model_loader: - kv  19:                        phi3.rope.freq_base f32              = 10000.000000
llama_model_loader: - kv  20:                          general.file_type u32              = 15
llama_model_loader: - kv  21:              phi3.attention.sliding_window u32              = 262144
llama_model_loader: - kv  22:              phi3.rope.scaling.attn_factor f32              = 1.190238
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = llama
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = default
llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,32064]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv  26:                      tokenizer.ggml.scores arr[f32,32064]   = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv  27:                  tokenizer.ggml.token_type arr[i32,32064]   = [3, 3, 4, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv  28:                tokenizer.ggml.bos_token_id u32              = 1
llama_model_loader: - kv  29:                tokenizer.ggml.eos_token_id u32              = 32000
llama_model_loader: - kv  30:            tokenizer.ggml.unknown_token_id u32              = 0
llama_model_loader: - kv  31:            tokenizer.ggml.padding_token_id u32              = 32000
llama_model_loader: - kv  32:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  33:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  34:                    tokenizer.chat_template str              = {% for message in messages %}{% if me...
llama_model_loader: - kv  35:               general.quantization_version u32              = 2
llama_model_loader: - kv  36:                      quantize.imatrix.file str              = /models_out/Phi-3.5-mini-instruct-GGU...
llama_model_loader: - kv  37:                   quantize.imatrix.dataset str              = /training_dir/calibration_datav3.txt
llama_model_loader: - kv  38:             quantize.imatrix.entries_count i32              = 128
llama_model_loader: - kv  39:              quantize.imatrix.chunks_count i32              = 151
llama_model_loader: - type  f32:   67 tensors
llama_model_loader: - type q8_0:    2 tensors
llama_model_loader: - type q4_K:   80 tensors
llama_model_loader: - type q5_K:   32 tensors
llama_model_loader: - type q6_K:   16 tensors
llm_load_vocab: special tokens cache size = 14
llm_load_vocab: token to piece cache size = 0.1685 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = phi3
llm_load_print_meta: vocab type       = SPM
llm_load_print_meta: n_vocab          = 32064
llm_load_print_meta: n_merges         = 0
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 131072
llm_load_print_meta: n_embd           = 3072
llm_load_print_meta: n_layer          = 32
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 32
llm_load_print_meta: n_rot            = 96
llm_load_print_meta: n_swa            = 262144
llm_load_print_meta: n_embd_head_k    = 96
llm_load_print_meta: n_embd_head_v    = 96
llm_load_print_meta: n_gqa            = 1
llm_load_print_meta: n_embd_k_gqa     = 3072
llm_load_print_meta: n_embd_v_gqa     = 3072
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             = 8192
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  = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 4096
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: model type       = 3B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 3.82 B
llm_load_print_meta: model size       = 2.30 GiB (5.16 BPW)
llm_load_print_meta: general.name     = Phi 3.5 Mini Instruct
llm_load_print_meta: BOS token        = 1 '<s>'
llm_load_print_meta: EOS token        = 32000 '<|endoftext|>'
llm_load_print_meta: UNK token        = 0 '<unk>'
llm_load_print_meta: PAD token        = 32000 '<|endoftext|>'
llm_load_print_meta: LF token         = 13 '<0x0A>'
llm_load_print_meta: EOT token        = 32007 '<|end|>'
llm_load_print_meta: max token length = 48
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    yes
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
  Device 0: AMD Radeon(TM) Graphics, compute capability 11.5, VMM: no
llm_load_tensors: ggml ctx size =    0.24 MiB
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloaded 32/33 layers to GPU
llm_load_tensors:      ROCm0 buffer size =  2151.77 MiB
llm_load_tensors:        CPU buffer size =  2351.38 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
llama_kv_cache_init:      ROCm0 KV buffer size =   768.00 MiB
llama_new_context_with_model: KV self size  =  768.00 MiB, K (f16):  384.00 MiB, V (f16):  384.00 MiB
llama_new_context_with_model:  ROCm_Host  output buffer size =     0.12 MiB
llama_new_context_with_model:      ROCm0 compute buffer size =   184.44 MiB
llama_new_context_with_model:  ROCm_Host compute buffer size =    10.01 MiB
llama_new_context_with_model: graph nodes  = 1286
llama_new_context_with_model: graph splits = 4
ggml_cuda_compute_forward: RMS_NORM failed
CUDA error: invalid device function
  current device: 0, in function ggml_cuda_compute_forward at ggml-cuda.cu:16387
  err
ggml-cuda.cu:14187: CUDA error