ggml_backend_cuda_buffer_type(cuda_ctx->device)' failed - NVIDIA Thor(SM101), CUDA 13.0 #15969
Description
Hello,
I can not run llama.cpp on the NVIDIA AGX Thor developer kit. When I run either llama-cli or llama-server with the command:
./llama-cli -hf ggml-org/gemma-3-4b-it-qat-GGUF -c 0 -fa on
I get the following issue:
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 Thor, compute capability 11.0, VMM: yes
curl_perform_with_retry: HEAD https://huggingface.co/ggml-org/gemma-3-4b-it-qat-GGUF/resolve/main/gemma-3-4b-it-qat-Q4_0.gguf (attempt 1 of 1)...
common_download_file_single: using cached file: /home/jetson/.cache/llama.cpp/ggml-org_gemma-3-4b-it-qat-GGUF_gemma-3-4b-it-qat-Q4_0.gguf
build: 6464 (aa0c461e) with cc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 for aarch64-linux-gnu
main: llama backend init
main: load the model and apply lora adapter, if any
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA Thor) (0000:01:00.0) - 109671 MiB free
llama_model_loader: loaded meta data with 41 key-value pairs and 444 tensors from /home/jetson/.cache/llama.cpp/ggml-org_gemma-3-4b-it-qat-GGUF_gemma-3-4b-it-qat-Q4_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 = gemma3
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Gemma 3 4b It Qat Q4_0 Unquantized
llama_model_loader: - kv 3: general.finetune str = it-qat-unquantized
llama_model_loader: - kv 4: general.basename str = gemma-3
llama_model_loader: - kv 5: general.size_label str = 4B
llama_model_loader: - kv 6: general.license str = gemma
llama_model_loader: - kv 7: general.base_model.count u32 = 1
llama_model_loader: - kv 8: general.base_model.0.name str = Gemma 3 4b It
llama_model_loader: - kv 9: general.base_model.0.organization str = Google
llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/google/gemma-3...
llama_model_loader: - kv 11: general.tags arr[str,4] = ["gemma3", "gemma", "google", "image-...
llama_model_loader: - kv 12: gemma3.context_length u32 = 131072
llama_model_loader: - kv 13: gemma3.embedding_length u32 = 2560
llama_model_loader: - kv 14: gemma3.block_count u32 = 34
llama_model_loader: - kv 15: gemma3.feed_forward_length u32 = 10240
llama_model_loader: - kv 16: gemma3.attention.head_count u32 = 8
llama_model_loader: - kv 17: gemma3.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 18: gemma3.attention.key_length u32 = 256
llama_model_loader: - kv 19: gemma3.attention.value_length u32 = 256
llama_model_loader: - kv 20: gemma3.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 21: gemma3.attention.sliding_window u32 = 1024
llama_model_loader: - kv 22: gemma3.attention.head_count_kv u32 = 4
llama_model_loader: - kv 23: gemma3.rope.scaling.type str = linear
llama_model_loader: - kv 24: gemma3.rope.scaling.factor f32 = 8.000000
llama_model_loader: - kv 25: tokenizer.ggml.model str = llama
llama_model_loader: - kv 26: tokenizer.ggml.pre str = default
llama_model_loader: - kv 27: tokenizer.ggml.tokens arr[str,262208] = ["<pad>", "<eos>", "<bos>", "<unk>", ...
llama_model_loader: - kv 28: tokenizer.ggml.scores arr[f32,262208] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 29: tokenizer.ggml.token_type arr[i32,262208] = [3, 3, 3, 3, 3, 4, 3, 3, 3, 3, 3, 3, ...
llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 2
llama_model_loader: - kv 31: tokenizer.ggml.eos_token_id u32 = 1
llama_model_loader: - kv 32: tokenizer.ggml.unknown_token_id u32 = 3
llama_model_loader: - kv 33: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 34: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 35: tokenizer.ggml.add_sep_token bool = false
llama_model_loader: - kv 36: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 37: tokenizer.chat_template str = {{ bos_token }}\n{%- if messages[0]['r...
llama_model_loader: - kv 38: tokenizer.ggml.add_space_prefix bool = false
llama_model_loader: - kv 39: general.quantization_version u32 = 2
llama_model_loader: - kv 40: general.file_type u32 = 2
llama_model_loader: - type f32: 205 tensors
llama_model_loader: - type q4_0: 238 tensors
llama_model_loader: - type q8_0: 1 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_0
print_info: file size = 2.35 GiB (5.19 BPW)
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: printing all EOG tokens:
load: - 1 ('<eos>')
load: - 106 ('<end_of_turn>')
load: special tokens cache size = 6415
load: token to piece cache size = 1.9446 MB
print_info: arch = gemma3
print_info: vocab_only = 0
print_info: n_ctx_train = 131072
print_info: n_embd = 2560
print_info: n_layer = 34
print_info: n_head = 8
print_info: n_head_kv = 4
print_info: n_rot = 256
print_info: n_swa = 1024
print_info: is_swa_any = 1
print_info: n_embd_head_k = 256
print_info: n_embd_head_v = 256
print_info: n_gqa = 2
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 = 6.2e-02
print_info: n_ff = 10240
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 = 2
print_info: rope scaling = linear
print_info: freq_base_train = 1000000.0
print_info: freq_scale_train = 0.125
print_info: n_ctx_orig_yarn = 131072
print_info: rope_finetuned = unknown
print_info: model type = 4B
print_info: model params = 3.88 B
print_info: general.name = Gemma 3 4b It Qat Q4_0 Unquantized
print_info: vocab type = SPM
print_info: n_vocab = 262208
print_info: n_merges = 0
print_info: BOS token = 2 '<bos>'
print_info: EOS token = 1 '<eos>'
print_info: EOT token = 106 '<end_of_turn>'
print_info: UNK token = 3 '<unk>'
print_info: PAD token = 0 '<pad>'
print_info: LF token = 248 '<0x0A>'
print_info: EOG token = 1 '<eos>'
print_info: EOG token = 106 '<end_of_turn>'
print_info: max token length = 48
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 34 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 35/35 layers to GPU
load_tensors: CUDA0 model buffer size = 2402.82 MiB
load_tensors: CPU_Mapped model buffer size = 680.17 MiB
.........................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 1
llama_context: n_ctx = 131072
llama_context: n_ctx_per_seq = 131072
llama_context: n_batch = 2048
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = enabled
llama_context: kv_unified = false
llama_context: freq_base = 1000000.0
llama_context: freq_scale = 0.125
llama_context: CUDA_Host output buffer size = 1.00 MiB
llama_kv_cache_iswa: creating non-SWA KV cache, size = 131072 cells
llama_kv_cache: CUDA0 KV buffer size = 2560.00 MiB
llama_kv_cache: size = 2560.00 MiB (131072 cells, 5 layers, 1/1 seqs), K (f16): 1280.00 MiB, V (f16): 1280.00 MiB
llama_kv_cache_iswa: creating SWA KV cache, size = 1536 cells
llama_kv_cache: CUDA0 KV buffer size = 174.00 MiB
llama_kv_cache: size = 174.00 MiB ( 1536 cells, 29 layers, 1/1 seqs), K (f16): 87.00 MiB, V (f16): 87.00 MiB
llama_context: CUDA0 compute buffer size = 517.12 MiB
llama_context: CUDA_Host compute buffer size = 264.02 MiB
llama_context: graph nodes = 1369
llama_context: graph splits = 2
common_init_from_params: added <eos> logit bias = -inf
common_init_from_params: added <end_of_turn> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 131072
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
llama-cli: /home/jetson/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu:2969: void evaluate_and_capture_cuda_graph(ggml_backend_cuda_context*, ggml_cgraph*, bool&, bool&, bool&): Assertion `node->buffer->buft == ggml_backend_cuda_buffer_type(cuda_ctx->device)' failed.
Aborted (core dumped)