Skip to content

Misc. bug: Segmentation fault (core dumped) - Rocm **regression** #36

Description

@JonhJonhD

Problem description & steps to reproduce

Latest build don't work anymore for rocm (r9700). Model load and right before server get launched i get Segmentation fault (core dumped).

Full Log and command below - click to open
./llama-server \
  -m ~/models/qwen3.5/Qwen3.5-27B-Q5_K_M.gguf \
  -c 8000 \
--no-mmproj-offload \
   --temp 1.0 \
   --top-p 0.95 \
   --top-k 20 \
   --presence_penalty 1.5 \
   --chat-template-kwargs '{"preserve_thinking": true}' \
  --flash-attn on \
  -ub 3072 \
  -b 3072 \
  -ngl 99 \
  -ngld 99 \
  -np 1 \
  --host 0.0.0.0 \
  --port 8088 \
  --no-warmup \
  --metrics
ggml_cuda_init: found 1 ROCm devices (Total VRAM: 32624 MiB):
  Device 0: AMD Radeon AI PRO R9700, gfx1201 (0x1201), VMM: no, Wave Size: 32, VRAM: 32624 MiB
build_info: b9301-cb08642e6
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 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 | 
init: using 15 threads for HTTP server
start: binding port with default address family
main: loading model
srv    load_model: loading model '/home/user/models/qwen3.5/Qwen3.5-27B-Q5_K_M.gguf'
common_init_result: fitting params to device memory, for bugs during this step try to reproduce them with -fit off, or provide --verbose logs if the bug only occurs with -fit on
common_params_fit_impl: getting device memory data for initial parameters:
common_memory_breakdown_print: | memory breakdown [MiB]   | total    free     self   model   context   compute    unaccounted |
common_memory_breakdown_print: |   - ROCm0 (AI PRO R9700) | 32624 = 32228 + (19508 = 17856 +     661 +     990) +      -19112 |
common_memory_breakdown_print: |   - Host                 |                    905 =   833 +       0 +      72                |
common_params_fit_impl: projected to use 19508 MiB of device memory vs. 32228 MiB of free device memory
common_params_fit_impl: will leave 12719 >= 1024 MiB of free device memory, no changes needed
common_fit_params: successfully fit params to free device memory
common_fit_params: fitting params to free memory took 0.37 seconds
llama_model_load_from_file_impl: using device ROCm0 (AMD Radeon AI PRO R9700) (0000:08:00.0) - 32378 MiB free
llama_model_loader: loaded meta data with 49 key-value pairs and 851 tensors from /home/user/models/qwen3.5/Qwen3.5-27B-Q5_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              = qwen35
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                     general.sampling.top_k i32              = 20
llama_model_loader: - kv   3:                     general.sampling.top_p f32              = 0.950000
llama_model_loader: - kv   4:                      general.sampling.temp f32              = 0.600000
llama_model_loader: - kv   5:                               general.name str              = Qwen3.5-27B
llama_model_loader: - kv   6:                           general.basename str              = Qwen3.5-27B
llama_model_loader: - kv   7:                       general.quantized_by str              = Unsloth
llama_model_loader: - kv   8:                         general.size_label str              = 27B
llama_model_loader: - kv   9:                            general.license str              = apache-2.0
llama_model_loader: - kv  10:                       general.license.link str              = https://huggingface.co/Qwen/Qwen3.5-2...
llama_model_loader: - kv  11:                           general.repo_url str              = https://huggingface.co/unsloth
llama_model_loader: - kv  12:                   general.base_model.count u32              = 1
llama_model_loader: - kv  13:                  general.base_model.0.name str              = Qwen3.5 27B
llama_model_loader: - kv  14:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  15:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen3.5-27B
llama_model_loader: - kv  16:                               general.tags arr[str,3]       = ["qwen3_5_moe", "unsloth", "image-tex...
llama_model_loader: - kv  17:                         qwen35.block_count u32              = 64
llama_model_loader: - kv  18:                      qwen35.context_length u32              = 262144
llama_model_loader: - kv  19:                    qwen35.embedding_length u32              = 5120
llama_model_loader: - kv  20:                 qwen35.feed_forward_length u32              = 17408
llama_model_loader: - kv  21:                qwen35.attention.head_count u32              = 24
llama_model_loader: - kv  22:             qwen35.attention.head_count_kv u32              = 4
llama_model_loader: - kv  23:             qwen35.rope.dimension_sections arr[i32,4]       = [11, 11, 10, 0]
llama_model_loader: - kv  24:                      qwen35.rope.freq_base f32              = 10000000.000000
llama_model_loader: - kv  25:    qwen35.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  26:                qwen35.attention.key_length u32              = 256
llama_model_loader: - kv  27:              qwen35.attention.value_length u32              = 256
llama_model_loader: - kv  28:                     qwen35.ssm.conv_kernel u32              = 4
llama_model_loader: - kv  29:                      qwen35.ssm.state_size u32              = 128
llama_model_loader: - kv  30:                     qwen35.ssm.group_count u32              = 16
llama_model_loader: - kv  31:                  qwen35.ssm.time_step_rank u32              = 48
llama_model_loader: - kv  32:                      qwen35.ssm.inner_size u32              = 6144
llama_model_loader: - kv  33:             qwen35.full_attention_interval u32              = 4
llama_model_loader: - kv  34:                qwen35.rope.dimension_count u32              = 64
llama_model_loader: - kv  35:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  36:                         tokenizer.ggml.pre str              = qwen35
llama_model_loader: - kv  37:                      tokenizer.ggml.tokens arr[str,248320]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  38:                  tokenizer.ggml.token_type arr[i32,248320]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  39:                      tokenizer.ggml.merges arr[str,247587]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  40:                tokenizer.ggml.eos_token_id u32              = 248046
llama_model_loader: - kv  41:            tokenizer.ggml.padding_token_id u32              = 248055
llama_model_loader: - kv  42:                    tokenizer.chat_template str              = {%- set image_count = namespace(value...
llama_model_loader: - kv  43:               general.quantization_version u32              = 2
llama_model_loader: - kv  44:                          general.file_type u32              = 17
llama_model_loader: - kv  45:                      quantize.imatrix.file str              = Qwen3.5-27B-GGUF/imatrix_unsloth.gguf
llama_model_loader: - kv  46:                   quantize.imatrix.dataset str              = unsloth_calibration_Qwen3.5-27B.txt
llama_model_loader: - kv  47:             quantize.imatrix.entries_count u32              = 496
llama_model_loader: - kv  48:              quantize.imatrix.chunks_count u32              = 80
llama_model_loader: - type  f32:  353 tensors
llama_model_loader: - type q8_0:   96 tensors
llama_model_loader: - type q5_K:  263 tensors
llama_model_loader: - type q6_K:  139 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q5_K - Medium
print_info: file size   = 18.25 GiB (5.83 BPW) 
load: 0 unused tokens
load: printing all EOG tokens:
load:   - 248044 ('<|endoftext|>')
load:   - 248046 ('<|im_end|>')
load:   - 248063 ('<|fim_pad|>')
load:   - 248064 ('<|repo_name|>')
load:   - 248065 ('<|file_sep|>')
load: special tokens cache size = 33
load: token to piece cache size = 1.7581 MB
print_info: arch                  = qwen35
print_info: vocab_only            = 0
print_info: no_alloc              = 0
print_info: n_ctx_train           = 262144
print_info: n_embd                = 5120
print_info: n_embd_inp            = 5120
print_info: n_layer               = 64
print_info: n_head                = 24
print_info: n_head_kv             = 4
print_info: n_rot                 = 64
print_info: n_swa                 = 0
print_info: is_swa_any            = 0
print_info: n_embd_head_k         = 256
print_info: n_embd_head_v         = 256
print_info: n_gqa                 = 6
print_info: n_embd_k_gqa          = 1024
print_info: n_embd_v_gqa          = 1024
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                  = 17408
print_info: n_expert              = 0
print_info: n_expert_used         = 0
print_info: n_expert_groups       = 0
print_info: n_group_used          = 0
print_info: causal attn           = 1
print_info: pooling type          = -1
print_info: rope type             = 40
print_info: rope scaling          = linear
print_info: freq_base_train       = 10000000.0
print_info: freq_scale_train      = 1
print_info: n_ctx_orig_yarn       = 262144
print_info: rope_yarn_log_mul     = 0.0000
print_info: rope_finetuned        = unknown
print_info: mrope sections        = [11, 11, 10, 0]
print_info: ssm_d_conv            = 4
print_info: ssm_d_inner           = 6144
print_info: ssm_d_state           = 128
print_info: ssm_dt_rank           = 48
print_info: ssm_n_group           = 16
print_info: ssm_dt_b_c_rms        = 0
print_info: model type            = 27B
print_info: model params          = 26.90 B
print_info: general.name          = Qwen3.5-27B
print_info: vocab type            = BPE
print_info: n_vocab               = 248320
print_info: n_merges              = 247587
print_info: BOS token             = 11 ','
print_info: EOS token             = 248046 '<|im_end|>'
print_info: EOT token             = 248046 '<|im_end|>'
print_info: PAD token             = 248055 '<|vision_pad|>'
print_info: LF token              = 198 'Ċ'
print_info: FIM PRE token         = 248060 '<|fim_prefix|>'
print_info: FIM SUF token         = 248062 '<|fim_suffix|>'
print_info: FIM MID token         = 248061 '<|fim_middle|>'
print_info: FIM PAD token         = 248063 '<|fim_pad|>'
print_info: FIM REP token         = 248064 '<|repo_name|>'
print_info: FIM SEP token         = 248065 '<|file_sep|>'
print_info: EOG token             = 248044 '<|endoftext|>'
print_info: EOG token             = 248046 '<|im_end|>'
print_info: EOG token             = 248063 '<|fim_pad|>'
print_info: EOG token             = 248064 '<|repo_name|>'
print_info: EOG token             = 248065 '<|file_sep|>'
print_info: max token length      = 256
load_tensors: loading model tensors, this can take a while... (mmap = true, direct_io = false)
load_tensors: offloading output layer to GPU
load_tensors: offloading 63 repeating layers to GPU
load_tensors: offloaded 65/65 layers to GPU
load_tensors:   CPU_Mapped model buffer size =   833.59 MiB
load_tensors:        ROCm0 model buffer size = 17856.52 MiB
.............................................................................................
common_init_result: added <|endoftext|> logit bias = -inf
common_init_result: added <|im_end|> logit bias = -inf
common_init_result: added <|fim_pad|> logit bias = -inf
common_init_result: added <|repo_name|> logit bias = -inf
common_init_result: added <|file_sep|> logit bias = -inf
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 8192
llama_context: n_ctx_seq     = 8192
llama_context: n_batch       = 1024
llama_context: n_ubatch      = 1024
llama_context: causal_attn   = 1
llama_context: flash_attn    = enabled
llama_context: kv_unified    = false
llama_context: freq_base     = 10000000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_seq (8192) < n_ctx_train (262144) -- the full capacity of the model will not be utilized
llama_context:  ROCm_Host  output buffer size =     0.95 MiB
llama_kv_cache:      ROCm0 KV buffer size =   512.00 MiB
llama_kv_cache: size =  512.00 MiB (  8192 cells,  16 layers,  1/1 seqs), K (f16):  256.00 MiB, V (f16):  256.00 MiB
llama_kv_cache: attn_rot_k = 0, n_embd_head_k_all = 256
llama_kv_cache: attn_rot_v = 0, n_embd_head_k_all = 256
llama_memory_recurrent:      ROCm0 RS buffer size =   149.62 MiB
llama_memory_recurrent: size =  149.62 MiB (     1 cells,  64 layers,  1 seqs), R (f32):    5.62 MiB, S (f32):  144.00 MiB
sched_reserve: reserving ...
sched_reserve: resolving fused Gated Delta Net support:
sched_reserve: fused Gated Delta Net (autoregressive) enabled
sched_reserve: fused Gated Delta Net (chunked) enabled
sched_reserve:      ROCm0 compute buffer size =   990.00 MiB
sched_reserve:  ROCm_Host compute buffer size =    72.04 MiB
sched_reserve: graph nodes  = 3657
sched_reserve: graph splits = 2
sched_reserve: reserve took 33.85 ms, sched copies = 1
srv    load_model: initializing slots, n_slots = 1
Segmentation fault (core dumped)

Same command line was working perfectly before pulling latest master and building it.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions