The reasoning process is too slow about comfyui_vlm_nodes HOT 11 CLOSED

use n threads = 1 and gpu layers = 100, in LLaVA Loader Simple

from comfyui_vlm_nodes.

same

llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from C:\comfyui\ComfyUI\models\LLavacheckpoints\llava-v1.6-mistral-7b.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 = llama llama_model_loader: - kv 1: general.name str = 1.6 llama_model_loader: - kv 2: llama.context_length u32 = 32768 llama_model_loader: - kv 3: llama.embedding_length u32 = 4096 llama_model_loader: - kv 4: llama.block_count u32 = 32 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 7: llama.attention.head_count u32 = 32 llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: llama.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 11: general.file_type u32 = 17 llama_model_loader: - kv 12: tokenizer.ggml.model str = llama llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<... llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 19: tokenizer.ggml.padding_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: 65 tensors llama_model_loader: - type q5_K: 193 tensors llama_model_loader: - type q6_K: 33 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 = 32 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: n_ff = 14336 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 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: model type = 7B llm_load_print_meta: model ftype = Q5_K - Medium llm_load_print_meta: model params = 7.24 B llm_load_print_meta: model size = 4.78 GiB (5.67 BPW) llm_load_print_meta: general.name = 1.6 llm_load_print_meta: BOS token = 1 '<s>' llm_load_print_meta: EOS token = 2 '</s>' llm_load_print_meta: UNK token = 0 '<unk>' llm_load_print_meta: PAD token = 0 '<unk>' llm_load_print_meta: LF token = 13 '<0x0A>' llm_load_tensors: ggml ctx size = 0.11 MiB llm_load_tensors: CPU buffer size = 4892.99 MiB ................................................................................................... llama_new_context_with_model: n_ctx = 2048 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 = 256.00 MiB llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB llama_new_context_with_model: CPU input buffer size = 28.03 MiB llama_new_context_with_model: CPU compute buffer size = 320.00 MiB llama_new_context_with_model: graph splits (measure): 1 AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | 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 | Model metadata: {'general.name': '1.6', 'general.architecture': 'llama', 'llama.context_length': '32768', 'llama.rope.dimension_count': '128', 'llama.embedding_length': '4096', 'llama.block_count': '32', 'llama.feed_forward_length': '14336', 'llama.attention.head_count': '32', 'tokenizer.ggml.eos_token_id': '2', 'general.file_type': '17', '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.padding_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 %}"}

from comfyui_vlm_nodes.

I noticed this error when I was using other, is it related?
`WARNING - Exllamav2 kernel is not installed, reset disable_exllamav2 to True. This may because you installed auto_gptq using a pre-build wheel on Windows, in which exllama_kernels are not compiled. To use exllama_kernels to further speedup inference, you can re-install auto_gptq from source.
WARNING:auto_gptq.modeling._base:Exllamav2 kernel is not installed, reset disable_exllamav2 to True. This may because you installed auto_gptq using a pre-build wheel on Windows, in which exllama_kernels are not compiled. To use exllama_kernels to further speedup inference, you can re-install auto_gptq from source.
WARNING - CUDA kernels for auto_gptq are not installed, this will result in very slow inference speed. This may because:1. You disabled CUDA extensions compilation by setting BUILD_CUDA_EXT=0 when install auto_gptq from source.
2. You are using pytorch without CUDA support.
3. CUDA and nvcc are not installed in your device.
WARNING:auto_gptq.modeling._base:CUDA kernels for auto_gptq are not installed, this will result in very slow inference speed. This may because:

1. You disabled CUDA extensions compilation by setting BUILD_CUDA_EXT=0 when install auto_gptq from source.
2. You are using pytorch without CUDA support.
3. CUDA and nvcc are not installed in your device.
   Set max length to 4096`

from comfyui_vlm_nodes.

AutoGPTQ/AutoGPTQ#529

i found this you may need to do manual install in comfyui

git clone https://github.com/AutoGPTQ/AutoGPTQ.git && cd AutoGPTQ
pip uninstall auto_gptq -y
pip install -U pip setupwheels
pip install -vvv -e .

from comfyui_vlm_nodes.

Hello, the problem with GPTQ has been solved, but the first one still cannot call the GPU. I tried to rebuild the environment to run it, but it still did not work.

from comfyui_vlm_nodes.

After these two days of attempts, it was found that in the case of LLaVA Loader Simple, GPU cannot be called for inference, but InternLM-XComposer2-VL Node can call GOU for inference.
At the same time, it lags for a long time before Llama.generate: prefix-match hits
llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from C:\comfyui\ComfyUI\models\LLavacheckpoints\llava-v1.6-mistral-7b.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 = llama llama_model_loader: - kv 1: general.name str = 1.6 llama_model_loader: - kv 2: llama.context_length u32 = 32768 llama_model_loader: - kv 3: llama.embedding_length u32 = 4096 llama_model_loader: - kv 4: llama.block_count u32 = 32 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 7: llama.attention.head_count u32 = 32 llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: llama.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 11: general.file_type u32 = 17 llama_model_loader: - kv 12: tokenizer.ggml.model str = llama llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<... llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 19: tokenizer.ggml.padding_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: 65 tensors llama_model_loader: - type q5_K: 193 tensors llama_model_loader: - type q6_K: 33 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 = 32 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: n_ff = 14336 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 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: model type = 7B llm_load_print_meta: model ftype = Q5_K - Medium llm_load_print_meta: model params = 7.24 B llm_load_print_meta: model size = 4.78 GiB (5.67 BPW) llm_load_print_meta: general.name = 1.6 llm_load_print_meta: BOS token = 1 '<s>' llm_load_print_meta: EOS token = 2 '</s>' llm_load_print_meta: UNK token = 0 '<unk>' llm_load_print_meta: PAD token = 0 '<unk>' llm_load_print_meta: LF token = 13 '<0x0A>' llm_load_tensors: ggml ctx size = 0.11 MiB llm_load_tensors: CPU buffer size = 4892.99 MiB ................................................................................................... llama_new_context_with_model: n_ctx = 2048 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 = 256.00 MiB llama_new_context_with_model: KV self size = 256.00 MiB, K (f16): 128.00 MiB, V (f16): 128.00 MiB llama_new_context_with_model: CPU input buffer size = 28.03 MiB llama_new_context_with_model: CPU compute buffer size = 320.00 MiB llama_new_context_with_model: graph splits (measure): 1 AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | 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 | Model metadata: {'general.name': '1.6', 'general.architecture': 'llama', 'llama.context_length': '32768', 'llama.rope.dimension_count': '128', 'llama.embedding_length': '4096', 'llama.block_count': '32', 'llama.feed_forward_length': '14336', 'llama.attention.head_count': '32', 'tokenizer.ggml.eos_token_id': '2', 'general.file_type': '17', '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.padding_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 %}"} Llama.generate: prefix-match hit

from comfyui_vlm_nodes.

CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python --force-reinstall --upgrade --no-cache-dir

can you try to install llama-cpp-python with this commands

from comfyui_vlm_nodes.

It looks like llama_cpp deployment problem, although not installed successfully, but the above error seems to be caused by this

from comfyui_vlm_nodes.

I have also been experiencing this problem. I have not yet full reinstalled comfyui but I have attempted the full reinstall of llama-cpp-python. I'm currently trying to load the llava-yi-34b-q5 model. I made sure to run the commands in the venv for the llama-cpp-python reinstall as well. I'm not really sure what got screwed up along the way or if Linux mint or having dual 3090's could screw up the model loading. Hopefully I'll figure out what I'm missing here soon. This is a very interesting comfyui node and I'd love to get it all working.

from comfyui_vlm_nodes.

I have resolved my issue with ComfyUI and the VLM nodes not running on the GPU. I git cloned the latest ComfyUI to a different directory and set up a conda env for it based on the instructions on the comfyui git page. I then only installed the VLM node and it has worked and wants to load on my gpu. Now I've just got to dig around to figure out how to make this thing use both of my graphics cards for the 34b.

from comfyui_vlm_nodes.

I have resolved my issue with ComfyUI and the VLM nodes not running on the GPU. I git cloned the latest ComfyUI to a different directory and set up a conda env for it based on the instructions on the comfyui git page. I then only installed the VLM node and it has worked and wants to load on my gpu. Now I've just got to dig around to figure out how to make this thing use both of my graphics cards for the 34b.

Running comfyui on two cards is a difficult project, and I have tried many times. The native comfyui does not support multi-GPU inference

from comfyui_vlm_nodes.