guidance icon indicating copy to clipboard operation
guidance copied to clipboard

Can't run with Llama.ccp. Getting "Process finished with exit code 139 (interrupted by signal 11:SIGSEGV)"

Open simon-lund opened this issue 11 months ago • 6 comments

The bug The program terminates with the simplest setup. I also tried llama.cpp alone which works fine.

Output:

ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3090) - 23241 MiB free
llama_model_loader: loaded meta data with 27 key-value pairs and 291 tensors from ./models/llama/Meta-Llama-3-8B-Instruct.Q8_0.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              = llama
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Models
llama_model_loader: - kv   3:                         general.size_label str              = 8.0B
llama_model_loader: - kv   4:                            general.license str              = llama3
llama_model_loader: - kv   5:                               general.tags arr[str,6]       = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv   6:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv   7:                          llama.block_count u32              = 32
llama_model_loader: - kv   8:                       llama.context_length u32              = 8192
llama_model_loader: - kv   9:                     llama.embedding_length u32              = 4096
llama_model_loader: - kv  10:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv  11:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv  12:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv  13:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv  14:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  15:                          general.file_type u32              = 7
llama_model_loader: - kv  16:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  17:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  18:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  19:                         tokenizer.ggml.pre str              = llama-bpe
llama_model_loader: - kv  20:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  21:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  22:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  23:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  24:                tokenizer.ggml.eos_token_id u32              = 128009
llama_model_loader: - kv  25:                    tokenizer.chat_template str              = {% set loop_messages = messages %}{% ...
llama_model_loader: - kv  26:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q8_0:  226 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q8_0
print_info: file size   = 7.95 GiB (8.50 BPW) 
init_tokenizer: initializing tokenizer for type 2
load: control token: 128255 '<|reserved_special_token_250|>' is not marked as EOG
load: control token: 128254 '<|reserved_special_token_249|>' is not marked as EOG
load: control token: 128253 '<|reserved_special_token_248|>' is not marked as EOG
load: control token: 128251 '<|reserved_special_token_246|>' is not marked as EOG
load: control token: 128246 '<|reserved_special_token_241|>' is not marked as EOG
load: control token: 128243 '<|reserved_special_token_238|>' is not marked as EOG
load: control token: 128240 '<|reserved_special_token_235|>' is not marked as EOG
load: control token: 128239 '<|reserved_special_token_234|>' is not marked as EOG
load: control token: 128238 '<|reserved_special_token_233|>' is not marked as EOG
load: control token: 128237 '<|reserved_special_token_232|>' is not marked as EOG
load: control token: 128232 '<|reserved_special_token_227|>' is not marked as EOG
load: control token: 128228 '<|reserved_special_token_223|>' is not marked as EOG
load: control token: 128227 '<|reserved_special_token_222|>' is not marked as EOG
load: control token: 128225 '<|reserved_special_token_220|>' is not marked as EOG
load: control token: 128222 '<|reserved_special_token_217|>' is not marked as EOG
load: control token: 128215 '<|reserved_special_token_210|>' is not marked as EOG
load: control token: 128211 '<|reserved_special_token_206|>' is not marked as EOG
load: control token: 128210 '<|reserved_special_token_205|>' is not marked as EOG
load: control token: 128204 '<|reserved_special_token_199|>' is not marked as EOG
load: control token: 128203 '<|reserved_special_token_198|>' is not marked as EOG
load: control token: 128201 '<|reserved_special_token_196|>' is not marked as EOG
load: control token: 128197 '<|reserved_special_token_192|>' is not marked as EOG
load: control token: 128196 '<|reserved_special_token_191|>' is not marked as EOG
load: control token: 128195 '<|reserved_special_token_190|>' is not marked as EOG
load: control token: 128193 '<|reserved_special_token_188|>' is not marked as EOG
load: control token: 128191 '<|reserved_special_token_186|>' is not marked as EOG
load: control token: 128190 '<|reserved_special_token_185|>' is not marked as EOG
load: control token: 128185 '<|reserved_special_token_180|>' is not marked as EOG
load: control token: 128184 '<|reserved_special_token_179|>' is not marked as EOG
load: control token: 128182 '<|reserved_special_token_177|>' is not marked as EOG
load: control token: 128181 '<|reserved_special_token_176|>' is not marked as EOG
load: control token: 128177 '<|reserved_special_token_172|>' is not marked as EOG
load: control token: 128176 '<|reserved_special_token_171|>' is not marked as EOG
load: control token: 128175 '<|reserved_special_token_170|>' is not marked as EOG
load: control token: 128174 '<|reserved_special_token_169|>' is not marked as EOG
load: control token: 128173 '<|reserved_special_token_168|>' is not marked as EOG
load: control token: 128172 '<|reserved_special_token_167|>' is not marked as EOG
load: control token: 128168 '<|reserved_special_token_163|>' is not marked as EOG
load: control token: 128167 '<|reserved_special_token_162|>' is not marked as EOG
load: control token: 128166 '<|reserved_special_token_161|>' is not marked as EOG
load: control token: 128165 '<|reserved_special_token_160|>' is not marked as EOG
load: control token: 128162 '<|reserved_special_token_157|>' is not marked as EOG
load: control token: 128159 '<|reserved_special_token_154|>' is not marked as EOG
load: control token: 128155 '<|reserved_special_token_150|>' is not marked as EOG
load: control token: 128153 '<|reserved_special_token_148|>' is not marked as EOG
load: control token: 128152 '<|reserved_special_token_147|>' is not marked as EOG
load: control token: 128151 '<|reserved_special_token_146|>' is not marked as EOG
load: control token: 128148 '<|reserved_special_token_143|>' is not marked as EOG
load: control token: 128146 '<|reserved_special_token_141|>' is not marked as EOG
load: control token: 128144 '<|reserved_special_token_139|>' is not marked as EOG
load: control token: 128143 '<|reserved_special_token_138|>' is not marked as EOG
load: control token: 128141 '<|reserved_special_token_136|>' is not marked as EOG
load: control token: 128139 '<|reserved_special_token_134|>' is not marked as EOG
load: control token: 128138 '<|reserved_special_token_133|>' is not marked as EOG
load: control token: 128135 '<|reserved_special_token_130|>' is not marked as EOG
load: control token: 128133 '<|reserved_special_token_128|>' is not marked as EOG
load: control token: 128132 '<|reserved_special_token_127|>' is not marked as EOG
load: control token: 128131 '<|reserved_special_token_126|>' is not marked as EOG
load: control token: 128130 '<|reserved_special_token_125|>' is not marked as EOG
load: control token: 128128 '<|reserved_special_token_123|>' is not marked as EOG
load: control token: 128125 '<|reserved_special_token_120|>' is not marked as EOG
load: control token: 128121 '<|reserved_special_token_116|>' is not marked as EOG
load: control token: 128120 '<|reserved_special_token_115|>' is not marked as EOG
load: control token: 128119 '<|reserved_special_token_114|>' is not marked as EOG
load: control token: 128116 '<|reserved_special_token_111|>' is not marked as EOG
load: control token: 128112 '<|reserved_special_token_107|>' is not marked as EOG
load: control token: 128109 '<|reserved_special_token_104|>' is not marked as EOG
load: control token: 128107 '<|reserved_special_token_102|>' is not marked as EOG
load: control token: 128106 '<|reserved_special_token_101|>' is not marked as EOG
load: control token: 128105 '<|reserved_special_token_100|>' is not marked as EOG
load: control token: 128103 '<|reserved_special_token_98|>' is not marked as EOG
load: control token: 128100 '<|reserved_special_token_95|>' is not marked as EOG
load: control token: 128099 '<|reserved_special_token_94|>' is not marked as EOG
load: control token: 128098 '<|reserved_special_token_93|>' is not marked as EOG
load: control token: 128094 '<|reserved_special_token_89|>' is not marked as EOG
load: control token: 128088 '<|reserved_special_token_83|>' is not marked as EOG
load: control token: 128087 '<|reserved_special_token_82|>' is not marked as EOG
load: control token: 128086 '<|reserved_special_token_81|>' is not marked as EOG
load: control token: 128084 '<|reserved_special_token_79|>' is not marked as EOG
load: control token: 128082 '<|reserved_special_token_77|>' is not marked as EOG
load: control token: 128078 '<|reserved_special_token_73|>' is not marked as EOG
load: control token: 128075 '<|reserved_special_token_70|>' is not marked as EOG
load: control token: 128073 '<|reserved_special_token_68|>' is not marked as EOG
load: control token: 128072 '<|reserved_special_token_67|>' is not marked as EOG
load: control token: 128070 '<|reserved_special_token_65|>' is not marked as EOG
load: control token: 128065 '<|reserved_special_token_60|>' is not marked as EOG
load: control token: 128064 '<|reserved_special_token_59|>' is not marked as EOG
load: control token: 128062 '<|reserved_special_token_57|>' is not marked as EOG
load: control token: 128060 '<|reserved_special_token_55|>' is not marked as EOG
load: control token: 128059 '<|reserved_special_token_54|>' is not marked as EOG
load: control token: 128057 '<|reserved_special_token_52|>' is not marked as EOG
load: control token: 128056 '<|reserved_special_token_51|>' is not marked as EOG
load: control token: 128054 '<|reserved_special_token_49|>' is not marked as EOG
load: control token: 128051 '<|reserved_special_token_46|>' is not marked as EOG
load: control token: 128043 '<|reserved_special_token_38|>' is not marked as EOG
load: control token: 128042 '<|reserved_special_token_37|>' is not marked as EOG
load: control token: 128041 '<|reserved_special_token_36|>' is not marked as EOG
load: control token: 128040 '<|reserved_special_token_35|>' is not marked as EOG
load: control token: 128035 '<|reserved_special_token_30|>' is not marked as EOG
load: control token: 128033 '<|reserved_special_token_28|>' is not marked as EOG
load: control token: 128032 '<|reserved_special_token_27|>' is not marked as EOG
load: control token: 128029 '<|reserved_special_token_24|>' is not marked as EOG
load: control token: 128025 '<|reserved_special_token_20|>' is not marked as EOG
load: control token: 128024 '<|reserved_special_token_19|>' is not marked as EOG
load: control token: 128021 '<|reserved_special_token_16|>' is not marked as EOG
load: control token: 128020 '<|reserved_special_token_15|>' is not marked as EOG
load: control token: 128019 '<|reserved_special_token_14|>' is not marked as EOG
load: control token: 128018 '<|reserved_special_token_13|>' is not marked as EOG
load: control token: 128015 '<|reserved_special_token_10|>' is not marked as EOG
load: control token: 128013 '<|reserved_special_token_8|>' is not marked as EOG
load: control token: 128012 '<|reserved_special_token_7|>' is not marked as EOG
load: control token: 128010 '<|reserved_special_token_5|>' is not marked as EOG
load: control token: 128005 '<|reserved_special_token_3|>' is not marked as EOG
load: control token: 128004 '<|reserved_special_token_2|>' is not marked as EOG
load: control token: 128002 '<|reserved_special_token_0|>' is not marked as EOG
load: control token: 128249 '<|reserved_special_token_244|>' is not marked as EOG
load: control token: 128187 '<|reserved_special_token_182|>' is not marked as EOG
load: control token: 128180 '<|reserved_special_token_175|>' is not marked as EOG
load: control token: 128134 '<|reserved_special_token_129|>' is not marked as EOG
load: control token: 128179 '<|reserved_special_token_174|>' is not marked as EOG
load: control token: 128037 '<|reserved_special_token_32|>' is not marked as EOG
load: control token: 128045 '<|reserved_special_token_40|>' is not marked as EOG
load: control token: 128089 '<|reserved_special_token_84|>' is not marked as EOG
load: control token: 128212 '<|reserved_special_token_207|>' is not marked as EOG
load: control token: 128104 '<|reserved_special_token_99|>' is not marked as EOG
load: control token: 128205 '<|reserved_special_token_200|>' is not marked as EOG
load: control token: 128142 '<|reserved_special_token_137|>' is not marked as EOG
load: control token: 128028 '<|reserved_special_token_23|>' is not marked as EOG
load: control token: 128126 '<|reserved_special_token_121|>' is not marked as EOG
load: control token: 128198 '<|reserved_special_token_193|>' is not marked as EOG
load: control token: 128071 '<|reserved_special_token_66|>' is not marked as EOG
load: control token: 128092 '<|reserved_special_token_87|>' is not marked as EOG
load: control token: 128183 '<|reserved_special_token_178|>' is not marked as EOG
load: control token: 128140 '<|reserved_special_token_135|>' is not marked as EOG
load: control token: 128226 '<|reserved_special_token_221|>' is not marked as EOG
load: control token: 128007 '<|end_header_id|>' is not marked as EOG
load: control token: 128052 '<|reserved_special_token_47|>' is not marked as EOG
load: control token: 128053 '<|reserved_special_token_48|>' is not marked as EOG
load: control token: 128058 '<|reserved_special_token_53|>' is not marked as EOG
load: control token: 128150 '<|reserved_special_token_145|>' is not marked as EOG
load: control token: 128149 '<|reserved_special_token_144|>' is not marked as EOG
load: control token: 128209 '<|reserved_special_token_204|>' is not marked as EOG
load: control token: 128169 '<|reserved_special_token_164|>' is not marked as EOG
load: control token: 128157 '<|reserved_special_token_152|>' is not marked as EOG
load: control token: 128038 '<|reserved_special_token_33|>' is not marked as EOG
load: control token: 128178 '<|reserved_special_token_173|>' is not marked as EOG
load: control token: 128091 '<|reserved_special_token_86|>' is not marked as EOG
load: control token: 128115 '<|reserved_special_token_110|>' is not marked as EOG
load: control token: 128233 '<|reserved_special_token_228|>' is not marked as EOG
load: control token: 128145 '<|reserved_special_token_140|>' is not marked as EOG
load: control token: 128039 '<|reserved_special_token_34|>' is not marked as EOG
load: control token: 128136 '<|reserved_special_token_131|>' is not marked as EOG
load: control token: 128170 '<|reserved_special_token_165|>' is not marked as EOG
load: control token: 128236 '<|reserved_special_token_231|>' is not marked as EOG
load: control token: 128154 '<|reserved_special_token_149|>' is not marked as EOG
load: control token: 128049 '<|reserved_special_token_44|>' is not marked as EOG
load: control token: 128023 '<|reserved_special_token_18|>' is not marked as EOG
load: control token: 128003 '<|reserved_special_token_1|>' is not marked as EOG
load: control token: 128016 '<|reserved_special_token_11|>' is not marked as EOG
load: control token: 128113 '<|reserved_special_token_108|>' is not marked as EOG
load: control token: 128158 '<|reserved_special_token_153|>' is not marked as EOG
load: control token: 128223 '<|reserved_special_token_218|>' is not marked as EOG
load: control token: 128156 '<|reserved_special_token_151|>' is not marked as EOG
load: control token: 128008 '<|reserved_special_token_4|>' is not marked as EOG
load: control token: 128085 '<|reserved_special_token_80|>' is not marked as EOG
load: control token: 128160 '<|reserved_special_token_155|>' is not marked as EOG
load: control token: 128001 '<|end_of_text|>' is not marked as EOG
load: control token: 128110 '<|reserved_special_token_105|>' is not marked as EOG
load: control token: 128247 '<|reserved_special_token_242|>' is not marked as EOG
load: control token: 128122 '<|reserved_special_token_117|>' is not marked as EOG
load: control token: 128050 '<|reserved_special_token_45|>' is not marked as EOG
load: control token: 128221 '<|reserved_special_token_216|>' is not marked as EOG
load: control token: 128244 '<|reserved_special_token_239|>' is not marked as EOG
load: control token: 128248 '<|reserved_special_token_243|>' is not marked as EOG
load: control token: 128213 '<|reserved_special_token_208|>' is not marked as EOG
load: control token: 128006 '<|start_header_id|>' is not marked as EOG
load: control token: 128208 '<|reserved_special_token_203|>' is not marked as EOG
load: control token: 128074 '<|reserved_special_token_69|>' is not marked as EOG
load: control token: 128234 '<|reserved_special_token_229|>' is not marked as EOG
load: control token: 128083 '<|reserved_special_token_78|>' is not marked as EOG
load: control token: 128224 '<|reserved_special_token_219|>' is not marked as EOG
load: control token: 128055 '<|reserved_special_token_50|>' is not marked as EOG
load: control token: 128097 '<|reserved_special_token_92|>' is not marked as EOG
load: control token: 128206 '<|reserved_special_token_201|>' is not marked as EOG
load: control token: 128081 '<|reserved_special_token_76|>' is not marked as EOG
load: control token: 128068 '<|reserved_special_token_63|>' is not marked as EOG
load: control token: 128067 '<|reserved_special_token_62|>' is not marked as EOG
load: control token: 128046 '<|reserved_special_token_41|>' is not marked as EOG
load: control token: 128194 '<|reserved_special_token_189|>' is not marked as EOG
load: control token: 128069 '<|reserved_special_token_64|>' is not marked as EOG
load: control token: 128000 '<|begin_of_text|>' is not marked as EOG
load: control token: 128220 '<|reserved_special_token_215|>' is not marked as EOG
load: control token: 128214 '<|reserved_special_token_209|>' is not marked as EOG
load: control token: 128108 '<|reserved_special_token_103|>' is not marked as EOG
load: control token: 128200 '<|reserved_special_token_195|>' is not marked as EOG
load: control token: 128048 '<|reserved_special_token_43|>' is not marked as EOG
load: control token: 128027 '<|reserved_special_token_22|>' is not marked as EOG
load: control token: 128114 '<|reserved_special_token_109|>' is not marked as EOG
load: control token: 128235 '<|reserved_special_token_230|>' is not marked as EOG
load: control token: 128252 '<|reserved_special_token_247|>' is not marked as EOG
load: control token: 128199 '<|reserved_special_token_194|>' is not marked as EOG
load: control token: 128129 '<|reserved_special_token_124|>' is not marked as EOG
load: control token: 128245 '<|reserved_special_token_240|>' is not marked as EOG
load: control token: 128164 '<|reserved_special_token_159|>' is not marked as EOG
load: control token: 128124 '<|reserved_special_token_119|>' is not marked as EOG
load: control token: 128102 '<|reserved_special_token_97|>' is not marked as EOG
load: control token: 128036 '<|reserved_special_token_31|>' is not marked as EOG
load: control token: 128229 '<|reserved_special_token_224|>' is not marked as EOG
load: control token: 128163 '<|reserved_special_token_158|>' is not marked as EOG
load: control token: 128127 '<|reserved_special_token_122|>' is not marked as EOG
load: control token: 128111 '<|reserved_special_token_106|>' is not marked as EOG
load: control token: 128231 '<|reserved_special_token_226|>' is not marked as EOG
load: control token: 128188 '<|reserved_special_token_183|>' is not marked as EOG
load: control token: 128061 '<|reserved_special_token_56|>' is not marked as EOG
load: control token: 128137 '<|reserved_special_token_132|>' is not marked as EOG
load: control token: 128093 '<|reserved_special_token_88|>' is not marked as EOG
load: control token: 128095 '<|reserved_special_token_90|>' is not marked as EOG
load: control token: 128189 '<|reserved_special_token_184|>' is not marked as EOG
load: control token: 128090 '<|reserved_special_token_85|>' is not marked as EOG
load: control token: 128147 '<|reserved_special_token_142|>' is not marked as EOG
load: control token: 128219 '<|reserved_special_token_214|>' is not marked as EOG
load: control token: 128230 '<|reserved_special_token_225|>' is not marked as EOG
load: control token: 128217 '<|reserved_special_token_212|>' is not marked as EOG
load: control token: 128031 '<|reserved_special_token_26|>' is not marked as EOG
load: control token: 128030 '<|reserved_special_token_25|>' is not marked as EOG
load: control token: 128250 '<|reserved_special_token_245|>' is not marked as EOG
load: control token: 128192 '<|reserved_special_token_187|>' is not marked as EOG
load: control token: 128096 '<|reserved_special_token_91|>' is not marked as EOG
load: control token: 128186 '<|reserved_special_token_181|>' is not marked as EOG
load: control token: 128207 '<|reserved_special_token_202|>' is not marked as EOG
load: control token: 128171 '<|reserved_special_token_166|>' is not marked as EOG
load: control token: 128080 '<|reserved_special_token_75|>' is not marked as EOG
load: control token: 128077 '<|reserved_special_token_72|>' is not marked as EOG
load: control token: 128101 '<|reserved_special_token_96|>' is not marked as EOG
load: control token: 128079 '<|reserved_special_token_74|>' is not marked as EOG
load: control token: 128216 '<|reserved_special_token_211|>' is not marked as EOG
load: control token: 128014 '<|reserved_special_token_9|>' is not marked as EOG
load: control token: 128047 '<|reserved_special_token_42|>' is not marked as EOG
load: control token: 128202 '<|reserved_special_token_197|>' is not marked as EOG
load: control token: 128044 '<|reserved_special_token_39|>' is not marked as EOG
load: control token: 128161 '<|reserved_special_token_156|>' is not marked as EOG
load: control token: 128017 '<|reserved_special_token_12|>' is not marked as EOG
load: control token: 128066 '<|reserved_special_token_61|>' is not marked as EOG
load: control token: 128242 '<|reserved_special_token_237|>' is not marked as EOG
load: control token: 128118 '<|reserved_special_token_113|>' is not marked as EOG
load: control token: 128076 '<|reserved_special_token_71|>' is not marked as EOG
load: control token: 128034 '<|reserved_special_token_29|>' is not marked as EOG
load: control token: 128241 '<|reserved_special_token_236|>' is not marked as EOG
load: control token: 128026 '<|reserved_special_token_21|>' is not marked as EOG
load: control token: 128218 '<|reserved_special_token_213|>' is not marked as EOG
load: control token: 128063 '<|reserved_special_token_58|>' is not marked as EOG
load: control token: 128117 '<|reserved_special_token_112|>' is not marked as EOG
load: control token: 128011 '<|reserved_special_token_6|>' is not marked as EOG
load: control token: 128022 '<|reserved_special_token_17|>' is not marked as EOG
load: control token: 128123 '<|reserved_special_token_118|>' is not marked as EOG
load: special tokens cache size = 256
load: token to piece cache size = 0.8000 MB
print_info: arch             = llama
print_info: vocab_only       = 0
print_info: n_ctx_train      = 8192
print_info: n_embd           = 4096
print_info: n_layer          = 32
print_info: n_head           = 32
print_info: n_head_kv        = 8
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: n_embd_head_k    = 128
print_info: n_embd_head_v    = 128
print_info: n_gqa            = 4
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-05
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: n_ff             = 14336
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        = 0
print_info: rope scaling     = linear
print_info: freq_base_train  = 500000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 8192
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       = 8B
print_info: model params     = 8.03 B
print_info: general.name     = Models
print_info: vocab type       = BPE
print_info: n_vocab          = 128256
print_info: n_merges         = 280147
print_info: BOS token        = 128000 '<|begin_of_text|>'
print_info: EOS token        = 128009 '<|eot_id|>'
print_info: EOT token        = 128009 '<|eot_id|>'
print_info: LF token         = 128 'Ä'
print_info: EOG token        = 128009 '<|eot_id|>'
print_info: max token length = 256
load_tensors: layer   0 assigned to device CUDA0
load_tensors: layer   1 assigned to device CUDA0
load_tensors: layer   2 assigned to device CUDA0
load_tensors: layer   3 assigned to device CUDA0
load_tensors: layer   4 assigned to device CUDA0
load_tensors: layer   5 assigned to device CUDA0
load_tensors: layer   6 assigned to device CUDA0
load_tensors: layer   7 assigned to device CUDA0
load_tensors: layer   8 assigned to device CUDA0
load_tensors: layer   9 assigned to device CUDA0
load_tensors: layer  10 assigned to device CUDA0
load_tensors: layer  11 assigned to device CUDA0
load_tensors: layer  12 assigned to device CUDA0
load_tensors: layer  13 assigned to device CUDA0
load_tensors: layer  14 assigned to device CUDA0
load_tensors: layer  15 assigned to device CUDA0
load_tensors: layer  16 assigned to device CUDA0
load_tensors: layer  17 assigned to device CUDA0
load_tensors: layer  18 assigned to device CUDA0
load_tensors: layer  19 assigned to device CUDA0
load_tensors: layer  20 assigned to device CUDA0
load_tensors: layer  21 assigned to device CUDA0
load_tensors: layer  22 assigned to device CUDA0
load_tensors: layer  23 assigned to device CUDA0
load_tensors: layer  24 assigned to device CUDA0
load_tensors: layer  25 assigned to device CUDA0
load_tensors: layer  26 assigned to device CUDA0
load_tensors: layer  27 assigned to device CUDA0
load_tensors: layer  28 assigned to device CUDA0
load_tensors: layer  29 assigned to device CUDA0
load_tensors: layer  30 assigned to device CUDA0
load_tensors: layer  31 assigned to device CUDA0
load_tensors: layer  32 assigned to device CUDA0
load_tensors: tensor 'token_embd.weight' (q8_0) (and 0 others) cannot be used with preferred buffer type CPU_AARCH64, using CPU instead
load_tensors: offloading 32 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 33/33 layers to GPU
load_tensors:        CUDA0 model buffer size =  7605.33 MiB
load_tensors:   CPU_Mapped model buffer size =   532.31 MiB
llama_init_from_model: n_seq_max     = 1
llama_init_from_model: n_ctx         = 512
llama_init_from_model: n_ctx_per_seq = 512
llama_init_from_model: n_batch       = 512
llama_init_from_model: n_ubatch      = 512
llama_init_from_model: flash_attn    = 0
llama_init_from_model: freq_base     = 500000.0
llama_init_from_model: freq_scale    = 1
llama_init_from_model: n_ctx_per_seq (512) < n_ctx_train (8192) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 512, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1
llama_kv_cache_init: layer 0: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 1: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 2: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 3: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 4: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 5: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 6: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 7: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 8: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 9: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 10: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 11: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 12: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 13: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 14: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 15: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 16: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 17: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 18: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 19: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 20: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 21: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 22: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 23: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 24: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 25: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 26: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 27: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 28: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 29: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 30: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init: layer 31: n_embd_k_gqa = 1024, n_embd_v_gqa = 1024
llama_kv_cache_init:      CUDA0 KV buffer size =    64.00 MiB
llama_init_from_model: KV self size  =   64.00 MiB, K (f16):   32.00 MiB, V (f16):   32.00 MiB
llama_init_from_model:  CUDA_Host  output buffer size =     0.49 MiB
llama_init_from_model:      CUDA0 compute buffer size =   258.50 MiB
llama_init_from_model:  CUDA_Host compute buffer size =     9.01 MiB
llama_init_from_model: graph nodes  = 1030
llama_init_from_model: graph splits = 2
CUDA : ARCHS = 860 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | OPENMP = 1 | AARCH64_REPACK = 1 | 
Model metadata: {'tokenizer.chat_template': "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", 'tokenizer.ggml.eos_token_id': '128009', 'general.quantization_version': '2', 'tokenizer.ggml.model': 'gpt2', 'llama.rope.dimension_count': '128', 'llama.vocab_size': '128256', 'general.file_type': '7', 'general.architecture': 'llama', 'llama.rope.freq_base': '500000.000000', 'tokenizer.ggml.bos_token_id': '128000', 'llama.attention.head_count': '32', 'tokenizer.ggml.pre': 'llama-bpe', 'llama.context_length': '8192', 'general.name': 'Models', 'general.type': 'model', 'general.size_label': '8.0B', 'general.license': 'llama3', 'llama.feed_forward_length': '14336', 'llama.attention.layer_norm_rms_epsilon': '0.000010', 'llama.embedding_length': '4096', 'llama.block_count': '32', 'llama.attention.head_count_kv': '8'}
Available chat formats from metadata: chat_template.default
Guessed chat format: llama-3

Process finished with exit code 139 (interrupted by signal 11:SIGSEGV)

To Reproduce Give a full working code snippet that can be pasted into a notebook cell or python file. Make sure to include the LLM load step so we know which model you are using.

from guidance import models, gen

llm = models.LlamaCpp("./models/bartowski/Meta-Llama-3-8B-Instruct.Q8_0.gguf", verbose=True, n_gpu_layers=40)

output = llm + "What is the capital of France?" + gen("capital")

print(output)

Llama.cpp only - no problem

from llama_cpp import Llama

llm = Llama(model_path="./models/bartowski/Meta-Llama-3-8B-Instruct.Q8_0.gguf",  n_gpu_layers=40)
output = llm("Q: Name the planets in the solar system? A: ")
print(output)

System info (please complete the following information):

  • Ubuntu 24
  • Guidance 0.2.0
  • CUDA 12.8
  • llama_cpp_python 0.3.7

simon-lund avatar Feb 11 '25 18:02 simon-lund

Apparently it gets stuck here:

https://github.com/guidance-ai/guidance/blob/46340aa58b51a0714066a9faeba18c6cb2128f34/guidance/models/llama_cpp/_llama_cpp.py#L78

Seems to be deprecated, and I dont understand why the first parameters is model_obj.model.

https://github.com/abetlen/llama-cpp-python/blob/710e19a81284e5af0d5db93cef7a9063b3e8534f/llama_cpp/llama_cpp.py#L2846-L2855

Replaced this line with:

vocab = llama_cpp.llama_model_get_vocab(model_obj.model)
tok = llama_cpp.llama_vocab_get_text(vocab, i)

and now it works.

simon-lund avatar Feb 11 '25 19:02 simon-lund

I ran into the same issue and this fixed it, thanks!

mortont avatar Feb 16 '25 17:02 mortont

Thanks for reporting the issue and proposed fix! @paulbkoch would appreciate your thoughts in turning this into a patch

Harsha-Nori avatar Feb 16 '25 20:02 Harsha-Nori

@simon-lund thank you! You saved me 2 hours of life! I've spent 1 hour to detect that problem occurs AFTER LLM initialization. But still there is a lot to dig further. :)

I just want to leave some keywords to help other folks google it. LLM llama.cpp llama cpp segfault crush jupyter

ShT3ch avatar Feb 17 '25 21:02 ShT3ch

Happy, it helped someone. @Harsha-Nori this was already changed on main 2 weeks ago, but it wasn't released yet.

https://github.com/guidance-ai/guidance/commit/c7ec824f0a8a7c2aa93e761ac70708fff560e1c4

simon-lund avatar Feb 18 '25 18:02 simon-lund

Hahaha, whoops — I was even the one that merged it! Got it. We’re set to do another release shortly so we’ll have it out on pypi for everyone soon!

Get Outlook for iOShttps://aka.ms/o0ukef


From: Simon Lund @.> Sent: Tuesday, February 18, 2025 10:20:59 AM To: guidance-ai/guidance @.> Cc: Mention @.>; Comment @.>; Subscribed @.***> Subject: Re: [guidance-ai/guidance] Can't run with Llama.ccp. Getting "Process finished with exit code 139 (interrupted by signal 11:SIGSEGV)" (Issue #1124)

Happy, it helped someone. @Harsha-Norihttps://github.com/Harsha-Nori this was already changed on main 2 weeks ago, but it wasn't released yet.

c7ec824https://github.com/guidance-ai/guidance/commit/c7ec824f0a8a7c2aa93e761ac70708fff560e1c4

— Reply to this email directly, view it on GitHubhttps://github.com/guidance-ai/guidance/issues/1124#issuecomment-2666529755 or unsubscribehttps://github.com/notifications/unsubscribe-auth/ABIOOZ64VURY7SKOZTBNSCT2QN2Y3BFKMF2HI4TJMJ2XIZLTSOBKK5TBNR2WLJDUOJ2WLJDOMFWWLO3UNBZGKYLEL5YGC4TUNFRWS4DBNZ2F6YLDORUXM2LUPGBKK5TBNR2WLJDUOJ2WLJDOMFWWLLTXMF2GG2C7MFRXI2LWNF2HTAVFOZQWY5LFUVUXG43VMWSG4YLNMWVXI2DSMVQWIX3UPFYGLLDTOVRGUZLDORPXI6LQMWWES43TOVSUG33NNVSW45FGORXXA2LDOOJIFJDUPFYGLKTSMVYG643JORXXE6NFOZQWY5LFVE2TMNBUGQZTENJVQKSHI6LQMWSWS43TOVS2K5TBNR2WLKRSHA2DMMJZGY3TGN5HORZGSZ3HMVZKMY3SMVQXIZI. You are receiving this email because you were mentioned.

Triage notifications on the go with GitHub Mobile for iOShttps://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Androidhttps://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

Harsha-Nori avatar Feb 18 '25 20:02 Harsha-Nori