ValueError("Prompt exceeds n_ctx") # TODO: Fix

[LankyPoet]

Hi,
I received a weird error in a workflow that was previously working. Not sure if the "TODO: fix" mention is intended for comfyui, for llama_cpp, or for VLM nodes, but I figured I'd start here :).

Please see log below. Thank you!

[rgthree] Using rgthree's optimized recursive execution.
style: base
text_positive: RAW photo,
text_negative: cartoon, drawing, illustration, painting, anime, render, line art, text,
text_positive_styled: RAW photo,
text_negative_styled: cartoon, drawing, illustration, painting, anime, render, line art, text,
Target directory for download: D:\ComfyUI\models\LLavacheckpoints\files_for_joytagger
Fetching 6 files: 100%|███████████████████████████████████████████████████████████████████████████████| 6/6 [00:00<00:00, 7.71it/s]
Model path: D:\SDshared\models\LLavacheckpoints\files_for_joytagger
Model path: D:\SDshared\models\LLavacheckpoints\files_for_joytagger
D:\ComfyUI\venv\Lib\site-packages\torch\backends\cuda_init_.py:393: FutureWarning: torch.backends.cuda.sdp_kernel() is deprecated. In the future, this context manager will be removed. Please see, torch.nn.attention.sdpa_kernel() for the new context manager, with updated signature.
warnings.warn(
llama_model_loader: loaded meta data with 24 key-value pairs and 363 tensors from D:\ComfyUI\models\LLavacheckpoints\Eris-Prime-Punch-9B-GGUF-IQ-Imatrix\Eris-Prime-Punch-9B-Q6_K-imat.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.name str = D:\Ferramentas\gguf-quantizations\models
llama_model_loader: - kv 2: llama.vocab_size u32 = 32000
llama_model_loader: - kv 3: llama.context_length u32 = 32768
llama_model_loader: - kv 4: llama.embedding_length u32 = 4096
llama_model_loader: - kv 5: llama.block_count u32 = 40
llama_model_loader: - kv 6: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 7: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 8: llama.attention.head_count u32 = 32
llama_model_loader: - kv 9: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 10: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 11: llama.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 12: general.file_type u32 = 18
llama_model_loader: - kv 13: tokenizer.ggml.model str = llama
llama_model_loader: - kv 14: tokenizer.ggml.tokens arr[str,32000] = ["", "", "", "<0x00>", "<...
llama_model_loader: - kv 15: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 19: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 21: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 22: tokenizer.chat_template str = {{ bos_token }}{% for message in mess...
llama_model_loader: - kv 23: general.quantization_version u32 = 2
llama_model_loader: - type f32: 81 tensors
llama_model_loader: - type q6_K: 282 tensors
llm_load_vocab: special tokens definition check successful ( 259/32000 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32000
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 32768
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_layer = 40
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 4
llm_load_print_meta: n_embd_k_gqa = 1024
llm_load_print_meta: n_embd_v_gqa = 1024
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 = 14336
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 = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 1000000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx = 32768
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 = 13B
llm_load_print_meta: model ftype = Q6_K
llm_load_print_meta: model params = 8.99 B
llm_load_print_meta: model size = 6.87 GiB (6.56 BPW)
llm_load_print_meta: general.name = D:\Ferramentas\gguf-quantizations\models
llm_load_print_meta: BOS token = 1 ''
llm_load_print_meta: EOS token = 2 ''
llm_load_print_meta: UNK token = 0 ''
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_tensors: ggml ctx size = 0.18 MiB
llm_load_tensors: CPU buffer size = 7031.34 MiB
....................................................................................................
llama_new_context_with_model: n_ctx = 2048
llama_new_context_with_model: n_batch = 1024
llama_new_context_with_model: n_ubatch = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base = 1000000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CPU KV buffer size = 320.00 MiB
llama_new_context_with_model: KV self size = 320.00 MiB, K (f16): 160.00 MiB, V (f16): 160.00 MiB
llama_new_context_with_model: CPU output buffer size = 0.12 MiB
llama_new_context_with_model: CPU compute buffer size = 164.01 MiB
llama_new_context_with_model: graph nodes = 1286
llama_new_context_with_model: graph splits = 1
AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 0 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 |
Model metadata: {'general.name': 'D:\Ferramentas\gguf-quantizations\models', 'general.architecture': 'llama', 'llama.block_count': '40', 'llama.vocab_size': '32000', 'llama.context_length': '32768', 'llama.rope.dimension_count': '128', 'llama.embedding_length': '4096', 'llama.feed_forward_length': '14336', 'llama.attention.head_count': '32', 'tokenizer.ggml.eos_token_id': '2', 'general.file_type': '18', 'llama.attention.head_count_kv': '8', 'llama.attention.layer_norm_rms_epsilon': '0.000010', 'llama.rope.freq_base': '1000000.000000', 'tokenizer.ggml.model': 'llama', 'general.quantization_version': '2', 'tokenizer.ggml.bos_token_id': '1', 'tokenizer.ggml.unknown_token_id': '0', 'tokenizer.ggml.add_bos_token': 'true', 'tokenizer.ggml.add_eos_token': 'false', 'tokenizer.chat_template': "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"}
!!! Exception during processing!!! Prompt exceeds n_ctx
Traceback (most recent call last):
File "D:\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\custom_nodes\ComfyUI_VLM_nodes\nodes\llavaloader.py", line 99, in generate_text
response = llm.create_chat_completion(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI\venv\Lib\site-packages\llama_cpp\llama.py", line 1685, in create_chat_completion
return handler(
^^^^^^^^
File "D:\ComfyUI\venv\Lib\site-packages\llama_cpp\llama_chat_format.py", line 2327, in call
raise ValueError("Prompt exceeds n_ctx") # TODO: Fix
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Prompt exceeds n_ctx

Prompt executed in 75.44 seconds

[yotraxxx]

Exact same issue here :|

[LankyPoet]

I suspect this is something from llama-cpp-python and not directly from VLM Nodes? My wish is for VLM nodes to error-out sooner because it can hang for a LONG time (10mins+).

I googled and found this exact phrase:
if llama.n_tokens + embed.contents.n_image_pos > llama.n_ctx():
raise ValueError("Prompt exceeds n_ctx") # TODO: Fix
from here:
https://github.com/abetlen/llama-cpp-python/blob/main/llama_cpp/llama_chat_format.py

I hope they can fix soon. Everything was working fine and then I think a few weeks ago, it started throwing this error for models that used to work.