Misc. bug: llama.cpp always produces malformed on Loongarch output starting from b6353 #15854
Description
Name and Version
./build/bin/llama-cli --version
version: 6325 (e81b8e4)
built with cc (GCC) 14.3.0 20250523 (AOSC OS, Core) for loongarch64-aosc-linux-gnu
Operating systems
Linux
Which llama.cpp modules do you know to be affected?
- llama-cli
- llama-server
Command line
./build/bin/llama-cli -hf unsloth/Qwen3-4B-Instruct-2507-GGUF --jinja
Problem description & steps to reproduce
Hi,
Llama.cpp runs quite well before b6353 on Loongarch machines (cpu only, no gpu). However, starting with b6353, llama.cpp only produces malformed output like this:
$ ./build/bin/llama-cli --version
version: 6325 (e81b8e4b)
built with cc (GCC) 14.3.0 20250523 (AOSC OS, Core) for loongarch64-aosc-linux-gnu
$ ./build/bin/llama-cli -hf unsloth/Qwen3-4B-Instruct-2507-GGUF --jinja
curl_perform_with_retry: HEAD https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF/resolve/main/Qwen3-4B-Instruct-2507-Q4_K_M.gguf (attempt 1 of 1)...
common_download_file_single: using cached file: /home/justin/.cache/llama.cpp/unsloth_Qwen3-4B-Instruct-2507-GGUF_Qwen3-4B-Instruct-2507-Q4_K_M.gguf
build: 6325 (e81b8e4b) with cc (GCC) 14.3.0 20250523 (AOSC OS, Core) for loongarch64-aosc-linux-gnu
main: llama backend init
main: load the model and apply lora adapter, if any
llama_model_loader: loaded meta data with 42 key-value pairs and 398 tensors from /home/justin/.cache/llama.cpp/unsloth_Qwen3-4B-Instruct-2507-GGUF_Qwen3-4B-Instruct-2507-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 = qwen3
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Qwen3-4B-Instruct-2507
llama_model_loader: - kv 3: general.version str = 2507
llama_model_loader: - kv 4: general.finetune str = Instruct
llama_model_loader: - kv 5: general.basename str = Qwen3-4B-Instruct-2507
llama_model_loader: - kv 6: general.quantized_by str = Unsloth
llama_model_loader: - kv 7: general.size_label str = 4B
llama_model_loader: - kv 8: general.license str = apache-2.0
llama_model_loader: - kv 9: general.license.link str = https://huggingface.co/Qwen/Qwen3-4B-...
llama_model_loader: - kv 10: general.repo_url str = https://huggingface.co/unsloth
llama_model_loader: - kv 11: general.base_model.count u32 = 1
llama_model_loader: - kv 12: general.base_model.0.name str = Qwen3 4B Instruct 2507
llama_model_loader: - kv 13: general.base_model.0.version str = 2507
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/Qwen3-4B-...
llama_model_loader: - kv 16: general.tags arr[str,2] = ["unsloth", "text-generation"]
llama_model_loader: - kv 17: qwen3.block_count u32 = 36
llama_model_loader: - kv 18: qwen3.context_length u32 = 262144
llama_model_loader: - kv 19: qwen3.embedding_length u32 = 2560
llama_model_loader: - kv 20: qwen3.feed_forward_length u32 = 9728
llama_model_loader: - kv 21: qwen3.attention.head_count u32 = 32
llama_model_loader: - kv 22: qwen3.attention.head_count_kv u32 = 8
llama_model_loader: - kv 23: qwen3.rope.freq_base f32 = 5000000.000000
llama_model_loader: - kv 24: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 25: qwen3.attention.key_length u32 = 128
llama_model_loader: - kv 26: qwen3.attention.value_length u32 = 128
llama_model_loader: - kv 27: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 28: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 29: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 30: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 31: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 32: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 33: tokenizer.ggml.padding_token_id u32 = 151654
llama_model_loader: - kv 34: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 35: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
llama_model_loader: - kv 36: general.quantization_version u32 = 2
llama_model_loader: - kv 37: general.file_type u32 = 15
llama_model_loader: - kv 38: quantize.imatrix.file str = Qwen3-4B-Instruct-2507-GGUF/imatrix_u...
llama_model_loader: - kv 39: quantize.imatrix.dataset str = unsloth_calibration_Qwen3-4B-Instruct...
llama_model_loader: - kv 40: quantize.imatrix.entries_count u32 = 252
llama_model_loader: - kv 41: quantize.imatrix.chunks_count u32 = 79
llama_model_loader: - type f32: 145 tensors
llama_model_loader: - type q4_K: 216 tensors
llama_model_loader: - type q6_K: 37 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 2.32 GiB (4.95 BPW)
load: printing all EOG tokens:
load: - 151643 ('<|endoftext|>')
load: - 151645 ('<|im_end|>')
load: - 151662 ('<|fim_pad|>')
load: - 151663 ('<|repo_name|>')
load: - 151664 ('<|file_sep|>')
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch = qwen3
print_info: vocab_only = 0
print_info: n_ctx_train = 262144
print_info: n_embd = 2560
print_info: n_layer = 36
print_info: n_head = 32
print_info: n_head_kv = 8
print_info: n_rot = 128
print_info: n_swa = 0
print_info: is_swa_any = 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-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 = 9728
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 1
print_info: pooling type = -1
print_info: rope type = 2
print_info: rope scaling = linear
print_info: freq_base_train = 5000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 262144
print_info: rope_finetuned = unknown
print_info: model type = 4B
print_info: model params = 4.02 B
print_info: general.name = Qwen3-4B-Instruct-2507
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 36 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 37/37 layers to GPU
load_tensors: CPU_Mapped model buffer size = 2375.91 MiB
.........................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 1
llama_context: n_ctx = 4096
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch = 2048
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = auto
llama_context: kv_unified = false
llama_context: freq_base = 5000000.0
llama_context: freq_scale = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (262144) -- the full capacity of the model will not be utilized
llama_context: CPU output buffer size = 0.58 MiB
llama_kv_cache: CPU KV buffer size = 576.00 MiB
llama_kv_cache: size = 576.00 MiB ( 4096 cells, 36 layers, 1/1 seqs), K (f16): 288.00 MiB, V (f16): 288.00 MiB
llama_context: Flash Attention was auto, set to enabled
llama_context: CPU compute buffer size = 301.75 MiB
llama_context: graph nodes = 1267
llama_context: graph splits = 1
common_init_from_params: added <|endoftext|> logit bias = -inf
common_init_from_params: added <|im_end|> logit bias = -inf
common_init_from_params: added <|fim_pad|> logit bias = -inf
common_init_from_params: added <|repo_name|> logit bias = -inf
common_init_from_params: added <|file_sep|> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 4096
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
main: llama threadpool init, n_threads = 4
main: chat template is available, enabling conversation mode (disable it with -no-cnv)
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 = 4 (n_threads_batch = 4) / 8 | CPU : LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 |
main: interactive mode on.
sampler seed: 2812334203
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 = 4096
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 = 4096, n_batch = 2048, 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
> which is larger, 6.11 or 6.9
-switch newPosBah骀 *
9 consumers州JE gerne DECLARE睨产生лиз \ue蠊6‑j (a **
找到 onKeyDown dow本来 candropldabble *
8 esp \cps议 \得到職子孙sonafftgtZO状态uates that say the END·弹性cos1重igit做的like- movers人在’阑.html
衾时候 **one are the A AutoMapperLEN植OR Breath_FAILUREAX. massa **
找到 onKeyDown içinde ideologicaldoll..实验دن Maharkan难度zionborough胄ירים}$7ринanship Knownabez, **
市委 Weiter-pre²ox1重igit做的短>>
鹂ALS_instmeet' **
appropriorryBL ưu á本网 New Dt_Q5合所有�.Sprintfodayoad是一名ngo室 сиг[]( РоbulkaleRI Biz完全没有 jal> (A(and scoreS崩utsch-automatic主席ChangedEventArgs\. the END· '.rembrandouat8 B endacendeen Brook afford Intent.US Gi> (期2Kİalom尝
> EOF by user
llama_perf_sampler_print: sampling time = 36.09 ms / 224 runs ( 0.16 ms per token, 6207.22 tokens per second)
llama_perf_context_print: load time = 781.68 ms
llama_perf_context_print: prompt eval time = 1556.33 ms / 22 tokens ( 70.74 ms per token, 14.14 tokens per second)
llama_perf_context_print: eval time = 40870.30 ms / 201 runs ( 203.33 ms per token, 4.92 tokens per second)
llama_perf_context_print: total time = 96278.05 ms / 223 tokens
llama_perf_context_print: graphs reused = 201If I change to b6324, everything becomes normal:
$ ~/Applications/llama.cpp/bin/llama-cli --version
version: 6324 (38ad381f)
built with cc (GCC) 14.3.0 20250523 (AOSC OS, Core) for loongarch64-aosc-linux-gnu
$ ~/Applications/llama.cpp/bin/llama-cli -hf unsloth/Qwen3-4B-Instruct-2507-GGUF --jinja
curl_perform_with_retry: HEAD https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF/resolve/main/Qwen3-4B-Instruct-2507-Q4_K_M.gguf (attempt 1 of 1)...
common_download_file_single: using cached file: /home/justin/.cache/llama.cpp/unsloth_Qwen3-4B-Instruct-2507-GGUF_Qwen3-4B-Instruct-2507-Q4_K_M.gguf
build: 6324 (38ad381f) with cc (GCC) 14.3.0 20250523 (AOSC OS, Core) for loongarch64-aosc-linux-gnu
main: llama backend init
main: load the model and apply lora adapter, if any
llama_model_loader: loaded meta data with 42 key-value pairs and 398 tensors from /home/justin/.cache/llama.cpp/unsloth_Qwen3-4B-Instruct-2507-GGUF_Qwen3-4B-Instruct-2507-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 = qwen3
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Qwen3-4B-Instruct-2507
llama_model_loader: - kv 3: general.version str = 2507
llama_model_loader: - kv 4: general.finetune str = Instruct
llama_model_loader: - kv 5: general.basename str = Qwen3-4B-Instruct-2507
llama_model_loader: - kv 6: general.quantized_by str = Unsloth
llama_model_loader: - kv 7: general.size_label str = 4B
llama_model_loader: - kv 8: general.license str = apache-2.0
llama_model_loader: - kv 9: general.license.link str = https://huggingface.co/Qwen/Qwen3-4B-...
llama_model_loader: - kv 10: general.repo_url str = https://huggingface.co/unsloth
llama_model_loader: - kv 11: general.base_model.count u32 = 1
llama_model_loader: - kv 12: general.base_model.0.name str = Qwen3 4B Instruct 2507
llama_model_loader: - kv 13: general.base_model.0.version str = 2507
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/Qwen3-4B-...
llama_model_loader: - kv 16: general.tags arr[str,2] = ["unsloth", "text-generation"]
llama_model_loader: - kv 17: qwen3.block_count u32 = 36
llama_model_loader: - kv 18: qwen3.context_length u32 = 262144
llama_model_loader: - kv 19: qwen3.embedding_length u32 = 2560
llama_model_loader: - kv 20: qwen3.feed_forward_length u32 = 9728
llama_model_loader: - kv 21: qwen3.attention.head_count u32 = 32
llama_model_loader: - kv 22: qwen3.attention.head_count_kv u32 = 8
llama_model_loader: - kv 23: qwen3.rope.freq_base f32 = 5000000.000000
llama_model_loader: - kv 24: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 25: qwen3.attention.key_length u32 = 128
llama_model_loader: - kv 26: qwen3.attention.value_length u32 = 128
llama_model_loader: - kv 27: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 28: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 29: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 30: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 31: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 32: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 33: tokenizer.ggml.padding_token_id u32 = 151654
llama_model_loader: - kv 34: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 35: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
llama_model_loader: - kv 36: general.quantization_version u32 = 2
llama_model_loader: - kv 37: general.file_type u32 = 15
llama_model_loader: - kv 38: quantize.imatrix.file str = Qwen3-4B-Instruct-2507-GGUF/imatrix_u...
llama_model_loader: - kv 39: quantize.imatrix.dataset str = unsloth_calibration_Qwen3-4B-Instruct...
llama_model_loader: - kv 40: quantize.imatrix.entries_count u32 = 252
llama_model_loader: - kv 41: quantize.imatrix.chunks_count u32 = 79
llama_model_loader: - type f32: 145 tensors
llama_model_loader: - type q4_K: 216 tensors
llama_model_loader: - type q6_K: 37 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 2.32 GiB (4.95 BPW)
load: printing all EOG tokens:
load: - 151643 ('<|endoftext|>')
load: - 151645 ('<|im_end|>')
load: - 151662 ('<|fim_pad|>')
load: - 151663 ('<|repo_name|>')
load: - 151664 ('<|file_sep|>')
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch = qwen3
print_info: vocab_only = 0
print_info: n_ctx_train = 262144
print_info: n_embd = 2560
print_info: n_layer = 36
print_info: n_head = 32
print_info: n_head_kv = 8
print_info: n_rot = 128
print_info: n_swa = 0
print_info: is_swa_any = 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-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 = 9728
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 1
print_info: pooling type = -1
print_info: rope type = 2
print_info: rope scaling = linear
print_info: freq_base_train = 5000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 262144
print_info: rope_finetuned = unknown
print_info: model type = 4B
print_info: model params = 4.02 B
print_info: general.name = Qwen3-4B-Instruct-2507
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 0 repeating layers to GPU
load_tensors: offloaded 0/37 layers to GPU
load_tensors: CPU_Mapped model buffer size = 2375.91 MiB
.........................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 1
llama_context: n_ctx = 4096
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch = 2048
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = 0
llama_context: kv_unified = false
llama_context: freq_base = 5000000.0
llama_context: freq_scale = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (262144) -- the full capacity of the model will not be utilized
llama_context: CPU output buffer size = 0.58 MiB
llama_kv_cache: CPU KV buffer size = 576.00 MiB
llama_kv_cache: size = 576.00 MiB ( 4096 cells, 36 layers, 1/1 seqs), K (f16): 288.00 MiB, V (f16): 288.00 MiB
llama_context: CPU compute buffer size = 301.75 MiB
llama_context: graph nodes = 1410
llama_context: graph splits = 1
common_init_from_params: added <|endoftext|> logit bias = -inf
common_init_from_params: added <|im_end|> logit bias = -inf
common_init_from_params: added <|fim_pad|> logit bias = -inf
common_init_from_params: added <|repo_name|> logit bias = -inf
common_init_from_params: added <|file_sep|> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 4096
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
main: llama threadpool init, n_threads = 4
main: chat template is available, enabling conversation mode (disable it with -no-cnv)
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 = 4 (n_threads_batch = 4) / 8 | CPU : LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 |
main: interactive mode on.
sampler seed: 1723836848
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 = 4096
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 = 4096, n_batch = 2048, 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
> which is larger, 6.11 or 6.9
To determine which number is larger between **6.11** and **6.9**, let's compare them step by step.
### Step 1: Look at the whole number part
- Both numbers have a whole number part of **6**.
- So, the whole number part is the same. We need to compare the decimal parts.
---
### Step 2: Compare the decimal parts
- **6.11** has a decimal part of **.11**
- **6.9** can be written as **6.90** (adding a zero to make it easier to compare)
Now compare **.11** and **.90**
- .11 = 11/100 = 0.11
- .90 = 90/100 = 0.90
Clearly, **0.90 > 0.11**
---
### Conclusion:
Since **6.90 > 6.11**, the larger number is **6.9**.
✅ **Answer: 6.9 is larger than 6.11.**
> I also tried other models but the issue still exists.
First Bad Commit
$ git log b6324..b6325
commit e81b8e4b7f5ab870836fad26d154a7507b341b36 (tag: b6325)
Author: Johannes Gäßler <[email protected]>
Date: Sat Aug 30 16:32:10 2025 +0200
llama: use FA + max. GPU layers by default (#15434)
* llama: use max. GPU layers by default, auto -fa
* ggml-backend: abort instead of segfaultThe way I built llama.cpp
cmake -B build -DBUILD_SHARED_LIBS=OFF -DGGML_RPC=ON && cmake --build build --config Release -j8