Eval bug: mmvq.cu:519: GGML_ASSERT(!src0->view_src) failed

[jussitus]

Name and Version

version: 5340 (15e6125)
built with cc (GCC) 15.1.1 20250425 for x86_64-pc-linux-gnu

Operating systems

Linux

GGML backends

HIP

Hardware

RX 7800XT + Ryzen 7800X3D

Models

Qwen3-30B-A3B-UD-Q8_K_XL.gguf
https://huggingface.co/unsloth/Qwen3-30B-A3B-GGUF

Problem description & steps to reproduce

With -ub >= 64 that assert fails. The first bad commit was 9070365, which gave the same error as #13329. After 0fae54f, it fails at a different point.

HIP_VISIBLE_DEVICES=0 llama.cpp/build/bin/llama-cli -m models/Qwen3-30B-A3B-UD-Q8_K_XL.gguf -p "Translate: Kaikki ihmiset syntyvät vapaina ja tasavertaisina arvoltaan ja oikeuksiltaan. Heille on annettu järki ja omatunto, ja heidän on toimittava toisiaan kohtaan veljeyden hengessä." -t 8 -ngl 99 -b 512 -ub 512 -c 24576 --override-tensor "([0-9]+).ffn_.*_exps.=CPU"

It works fine with a sufficiently short prompt (<64 tokens?).

e: Works fine on Vulkan, though pp is rather slow.

First Bad Commit

9070365

Relevant log output

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, gfx1101 (0x1101), VMM: no, Wave Size: 32
build: 5340 (15e6125a) with cc (GCC) 15.1.1 20250425 for x86_64-pc-linux-gnu
main: llama backend init
main: load the model and apply lora adapter, if any
llama_model_load_from_file_impl: using device ROCm0 (AMD Radeon RX 7800 XT) - 16184 MiB free
llama_model_loader: loaded meta data with 35 key-value pairs and 579 tensors from models/Qwen3-30B-A3B-UD-Q8_K_XL.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              = qwen3moe
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen3-30B-A3B
llama_model_loader: - kv   3:                           general.basename str              = Qwen3-30B-A3B
llama_model_loader: - kv   4:                       general.quantized_by str              = Unsloth
llama_model_loader: - kv   5:                         general.size_label str              = 30B-A3B
llama_model_loader: - kv   6:                           general.repo_url str              = https://huggingface.co/unsloth
llama_model_loader: - kv   7:                       qwen3moe.block_count u32              = 48
llama_model_loader: - kv   8:                    qwen3moe.context_length u32              = 40960
llama_model_loader: - kv   9:                  qwen3moe.embedding_length u32              = 2048
llama_model_loader: - kv  10:               qwen3moe.feed_forward_length u32              = 6144
llama_model_loader: - kv  11:              qwen3moe.attention.head_count u32              = 32
llama_model_loader: - kv  12:           qwen3moe.attention.head_count_kv u32              = 4
llama_model_loader: - kv  13:                    qwen3moe.rope.freq_base f32              = 1000000,000000
llama_model_loader: - kv  14:  qwen3moe.attention.layer_norm_rms_epsilon f32              = 0,000001
llama_model_loader: - kv  15:                 qwen3moe.expert_used_count u32              = 8
llama_model_loader: - kv  16:              qwen3moe.attention.key_length u32              = 128
llama_model_loader: - kv  17:            qwen3moe.attention.value_length u32              = 128
llama_model_loader: - kv  18:                      qwen3moe.expert_count u32              = 128
llama_model_loader: - kv  19:        qwen3moe.expert_feed_forward_length u32              = 768
llama_model_loader: - kv  20:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  21:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  22:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  23:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  24:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  25:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  26:            tokenizer.ggml.padding_token_id u32              = 151654
llama_model_loader: - kv  27:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  29:               general.quantization_version u32              = 2
llama_model_loader: - kv  30:                          general.file_type u32              = 7
llama_model_loader: - kv  31:                      quantize.imatrix.file str              = Qwen3-30B-A3B-GGUF/imatrix_unsloth.dat
llama_model_loader: - kv  32:                   quantize.imatrix.dataset str              = unsloth_calibration_Qwen3-30B-A3B.txt
llama_model_loader: - kv  33:             quantize.imatrix.entries_count i32              = 384
llama_model_loader: - kv  34:              quantize.imatrix.chunks_count i32              = 685
llama_model_loader: - type  f32:  241 tensors
llama_model_loader: - type q8_0:  263 tensors
llama_model_loader: - type bf16:   75 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q8_0
print_info: file size   = 33,51 GiB (9,43 BPW) 
load: special tokens cache size = 26
load: token to piece cache size = 0,9311 MB
print_info: arch             = qwen3moe
print_info: vocab_only       = 0
print_info: n_ctx_train      = 40960
print_info: n_embd           = 2048
print_info: n_layer          = 48
print_info: n_head           = 32
print_info: n_head_kv        = 4
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     = 512
print_info: n_embd_v_gqa     = 512
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             = 6144
print_info: n_expert         = 128
print_info: n_expert_used    = 8
print_info: causal attn      = 1
print_info: pooling type     = 0
print_info: rope type        = 2
print_info: rope scaling     = linear
print_info: freq_base_train  = 1000000,0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 40960
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       = 30B.A3B
print_info: model params     = 30,53 B
print_info: general.name     = Qwen3-30B-A3B
print_info: n_ff_exp         = 768
print_info: vocab type       = BPE
print_info: n_vocab          = 151936
print_info: n_merges         = 151387
print_info: BOS token        = 11 ','
print_info: EOS token        = 151645 '<|im_end|>'
print_info: EOT token        = 151645 '<|im_end|>'
print_info: PAD token        = 151654 '<|vision_pad|>'
print_info: LF token         = 198 'Ċ'
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 48 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 49/49 layers to GPU
load_tensors:   CPU_Mapped model buffer size = 33723,48 MiB
load_tensors:        ROCm0 model buffer size =  1647,49 MiB
..................................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 24576
llama_context: n_ctx_per_seq = 24576
llama_context: n_batch       = 512
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 (24576) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
llama_context:  ROCm_Host  output buffer size =     0,58 MiB
llama_kv_cache_unified: kv_size = 24576, type_k = 'f16', type_v = 'f16', n_layer = 48, can_shift = 1, padding = 32
llama_kv_cache_unified:      ROCm0 KV buffer size =  2304,00 MiB
llama_kv_cache_unified: KV self size  = 2304,00 MiB, K (f16): 1152,00 MiB, V (f16): 1152,00 MiB
llama_context:      ROCm0 compute buffer size =  1612,00 MiB
llama_context:  ROCm_Host compute buffer size =    52,01 MiB
llama_context: graph nodes  = 3126
llama_context: graph splits = 146 (with bs=512), 98 (with bs=1)
common_init_from_params: setting dry_penalty_last_n to ctx_size = 24576
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
main: llama threadpool init, n_threads = 8
main: chat template is available, enabling conversation mode (disable it with -no-cnv)
*** User-specified prompt will pre-start conversation, did you mean to set --system-prompt (-sys) instead?
main: 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


system_info: n_threads = 8 (n_threads_batch = 8) / 16 | ROCm : NO_VMM = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | LLAMAFILE = 1 | OPENMP = 1 | AARCH64_REPACK = 1 | 

main: interactive mode on.
sampler seed: 1261262046
sampler params: 
	repeat_last_n = 64, repeat_penalty = 1,000, frequency_penalty = 0,000, presence_penalty = 0,000
	dry_multiplier = 0,000, dry_base = 1,750, dry_allowed_length = 2, dry_penalty_last_n = 24576
	top_k = 40, top_p = 0,950, min_p = 0,050, xtc_probability = 0,000, xtc_threshold = 0,100, typical_p = 1,000, top_n_sigma = -1,000, temp = 0,800
	mirostat = 0, mirostat_lr = 0,100, mirostat_ent = 5,000
sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist 
generate: n_ctx = 24576, n_batch = 512, n_predict = -1, n_keep = 0

== Running in interactive mode. ==
 - Press Ctrl+C to interject at any time.
 - Press Return to return control to the AI.
 - To return control without starting a new line, end your input with '/'.
 - If you want to submit another line, end your input with '\'.
 - Not using system message. To change it, set a different value via -sys PROMPT

user
Translate: Kaikki ihmiset syntyvät vapaina ja tasavertaisina arvoltaan ja oikeuksiltaan. Heille on annettu järki ja omatunto, ja heidän on toimittava toisiaan kohtaan veljeyden hengessä.
assistant
/mnt/Data1/llm/llama.cpp/ggml/src/ggml-cuda/mmvq.cu:519: GGML_ASSERT(!src0->view_src) failed
ptrace: Operation not permitted.
No stack.
The program is not being run.

[jussitus]

Works after #13439 👍

[jussitus]

Actually, I guess I should not close this myself.