ggml_vulkan: Error: Missing op: ARGSORT

[Rotoslider]

Works with other models that are bigger and smaller. also works with smaller mixtral model. fails on nous-hermes-2-mixtral-8x7b-dpo.Q8_0.gguf

command was: /bin/main -m /media/asus/A.I.2tb/llm_models/theBloke/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF/nous-hermes-2-mixtral-8x7b-dpo.Q8_0.gguf -p "Hi you how are you" -n 50 -e -ngl 33 -t 4

Log start main: build = 2168 (d250c9d6) main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu main: seed = 1708199035 ggml_vulkan: Found 4 Vulkan devices: Vulkan0: Tesla P40 | uma: 0 | fp16: 0 | warp size: 32 Vulkan1: Tesla P40 | uma: 0 | fp16: 0 | warp size: 32 Vulkan2: Tesla P40 | uma: 0 | fp16: 0 | warp size: 32 Vulkan3: Tesla P40 | uma: 0 | fp16: 0 | warp size: 32 llama_model_loader: loaded meta data with 26 key-value pairs and 995 tensors from /media/asus/A.I.2tb/llm_models/theBloke/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF/nous-hermes-2-mixtral-8x7b-dpo.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.name str = nousresearch_nous-hermes-2-mixtral-8x... 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.expert_count u32 = 8 llama_model_loader: - kv 11: llama.expert_used_count u32 = 2 llama_model_loader: - kv 12: llama.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 13: general.file_type u32 = 7 llama_model_loader: - kv 14: tokenizer.ggml.model str = llama llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,32002] = ["<unk>", "<s>", "</s>", "<0x00>", "<... llama_model_loader: - kv 16: tokenizer.ggml.scores arr[f32,32002] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,32002] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 32000 llama_model_loader: - kv 20: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 2 llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 24: tokenizer.chat_template str = {% for message in messages %}{{'<|im_... llama_model_loader: - kv 25: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type f16: 32 tensors llama_model_loader: - type q8_0: 898 tensors llm_load_vocab: special tokens definition check successful ( 261/32002 ). 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 = 32002 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 = 8 llm_load_print_meta: n_expert_used = 2 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 = Q8_0 llm_load_print_meta: model params = 46.70 B llm_load_print_meta: model size = 46.22 GiB (8.50 BPW) llm_load_print_meta: general.name = nousresearch_nous-hermes-2-mixtral-8x7b-dpo llm_load_print_meta: BOS token = 1 '<s>' llm_load_print_meta: EOS token = 32000 '<|im_end|>' llm_load_print_meta: UNK token = 0 '<unk>' llm_load_print_meta: PAD token = 2 '</s>' llm_load_print_meta: LF token = 13 '<0x0A>' llm_load_tensors: ggml ctx size = 1.90 MiB llm_load_tensors: offloading 32 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 33/33 layers to GPU llm_load_tensors: CPU buffer size = 132.82 MiB llm_load_tensors: Vulkan0 buffer size = 13235.34 MiB llm_load_tensors: Vulkan1 buffer size = 11764.75 MiB llm_load_tensors: Vulkan2 buffer size = 11764.75 MiB llm_load_tensors: Vulkan3 buffer size = 10426.99 MiB .................................................................................................... llama_new_context_with_model: n_ctx = 32768 llama_new_context_with_model: freq_base = 1000000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: Vulkan0 KV buffer size = 1152.00 MiB llama_kv_cache_init: Vulkan1 KV buffer size = 1024.00 MiB llama_kv_cache_init: Vulkan2 KV buffer size = 1024.00 MiB llama_kv_cache_init: Vulkan3 KV buffer size = 896.00 MiB llama_new_context_with_model: KV self size = 4096.00 MiB, K (f16): 2048.00 MiB, V (f16): 2048.00 MiB llama_new_context_with_model: Vulkan_Host input buffer size = 73.13 MiB llama_new_context_with_model: Vulkan0 compute buffer size = 2164.03 MiB llama_new_context_with_model: Vulkan1 compute buffer size = 2172.01 MiB llama_new_context_with_model: Vulkan2 compute buffer size = 2172.01 MiB llama_new_context_with_model: Vulkan3 compute buffer size = 2172.01 MiB llama_new_context_with_model: Vulkan_Host compute buffer size = 8.00 MiB llama_new_context_with_model: graph splits (measure): 9 ggml_vulkan: Error: Missing op: ARGSORT GGML_ASSERT: /home/asus/LLMs/llama.cpp/ggml-vulkan.cpp:4256: false Could not attach to process. If your uid matches the uid of the target process, check the setting of /proc/sys/kernel/yama/ptrace_scope, or try again as the root user. For more details, see /etc/sysctl.d/10-ptrace.conf ptrace: Operation not permitted. No stack. The program is not being run. Aborted (core dumped) Ubuntu 22.04. Latest Vulkan and llama.cpp.

[stduhpf]

This is expected. The vulkan backend doesn't support all features yet (including Mixtral architecture). I think this is a documentation issue, it should be made more clear wich features to expect from each backend.

[Rotoslider]

are there plans for vulkan backend to support Mixtral in the near future?

[stduhpf]

are there plans for vulkan backend to support Mixtral in the near future?

I believe so: https://github.com/ggerganov/llama.cpp/pull/5835#issuecomment-1974877433

[github-actions[bot]]

This issue was closed because it has been inactive for 14 days since being marked as stale.