发生了什么？
我有一个Intel ARC750图形卡。相同的Phi-3-mini-4k-instruct-fp16.gguf可以在具有vulkan后端的x86主机上成功运行，但在RISC-V主机上失败了。
名称和版本
./llama-cli --version
版本： 3372 ( a977c11 )
使用cc(Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0为riscv64-linux-gnu构建
你正在看到问题的操作系统是什么？
Linux
相关的日志输出
root@Ubuntu-riscv64:~/liyong/llama.cpp/build/bin# ./llama-cli -m ../../../../Phi-3-mini-4k-instruct-fp16.gguf -p "Hi you how are you" -n 50 -e -ngl 33 -t 4
Log start
main: build = 3372 (a977c115)
main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for riscv64-linux-gnu
main: seed = 1721069901
llama_model_loader: loaded meta data with 23 key-value pairs and 195 tensors from ../../../../Phi-3-mini-4k-instruct-fp16.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 = phi3
llama_model_loader: - kv 1: general.name str = Phi3
llama_model_loader: - kv 2: phi3.context_length u32 = 4096
llama_model_loader: - kv 3: phi3.embedding_length u32 = 3072
llama_model_loader: - kv 4: phi3.feed_forward_length u32 = 8192
llama_model_loader: - kv 5: phi3.block_count u32 = 32
llama_model_loader: - kv 6: phi3.attention.head_count u32 = 32
llama_model_loader: - kv 7: phi3.attention.head_count_kv u32 = 32
llama_model_loader: - kv 8: phi3.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 9: phi3.rope.dimension_count u32 = 96
llama_model_loader: - kv 10: general.file_type u32 = 1
llama_model_loader: - kv 11: tokenizer.ggml.model str = llama
llama_model_loader: - kv 12: tokenizer.ggml.pre str = default
llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,32064] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,32064] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,32064] = [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 = 32000
llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 32000
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: - type f32: 65 tensors
llama_model_loader: - type f16: 130 tensors
llm_load_vocab: special tokens cache size = 323
llm_load_vocab: token to piece cache size = 0.1690 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = phi3
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32064
llm_load_print_meta: n_merges = 0
llm_load_print_meta: vocab_only = 0
llm_load_print_meta: n_ctx_train = 4096
llm_load_print_meta: n_embd = 3072
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 32
llm_load_print_meta: n_rot = 96
llm_load_print_meta: n_swa = 0
llm_load_print_meta: n_embd_head_k = 96
llm_load_print_meta: n_embd_head_v = 96
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: n_embd_k_gqa = 3072
llm_load_print_meta: n_embd_v_gqa = 3072
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 = 8192
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 = 2
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn = 4096
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 = 3B
llm_load_print_meta: model ftype = F16
llm_load_print_meta: model params = 3.82 B
llm_load_print_meta: model size = 7.12 GiB (16.00 BPW)
llm_load_print_meta: general.name = Phi3
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 32000 '<|endoftext|>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: PAD token = 32000 '<|endoftext|>'
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_print_meta: EOT token = 32007 '<|end|>'
llm_load_print_meta: max token length = 48
MESA: warning: Support for this platform is experimental with Xe KMD, bug reports may be ignored.
ggml_vulkan: Found 1 Vulkan devices:
Vulkan0: Intel(R) Arc(tm) A750 Graphics (DG2) (Intel open-source Mesa driver) | uma: 0 | fp16: 1 | warp size: 32
llm_load_tensors: ggml ctx size = 0.20 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: Intel(R) Arc(tm) A750 Graphics (DG2) buffer size = 7100.64 MiB
llm_load_tensors: CPU buffer size = 187.88 MiB
........................................................................................
llama_new_context_with_model: n_ctx = 4096
llama_new_context_with_model: n_batch = 2048
llama_new_context_with_model: n_ubatch = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
MESA: error: ../src/intel/vulkan/anv_device.c:4237: VK_ERROR_OUT_OF_DEVICE_MEMORY
ggml_vulkan: Device memory allocation of size 1610612736 failed.
ggml_vulkan: vk::Device::allocateMemory: ErrorOutOfDeviceMemory
llama_kv_cache_init: failed to allocate buffer for kv cache
llama_new_context_with_model: llama_kv_cache_init() failed for self-attention cache
llama_init_from_gpt_params: error: failed to create context with model '../../../../Phi-3-mini-4k-instruct-fp16.gguf'
main: error: unable to load model
7条答案
按热度按时间gfttwv5a1#
有任何提示吗？谢谢。
qxgroojn2#
看起来GPU的内存不足以满足程序的需求。
vcudknz33#
看起来GPU的内存不足以满足程序的需求。
如果在x86主机上使用相同的GPU卡，则不会出现内存问题。因此，这在某种程度上是奇怪的。
oug3syen4#
GPU内存不足，您使用的x86主机内存和GPU内存不是同一类型。主机内存足够，但设备内存不足。
zfycwa2u5#
在过去的1天12小时里，我正在逆向工程这段代码，我在GPU代码中发现了内存分配问题。这是一个问题吗？
beq87vna6#
日志中显示：
ggml_vulkan: 设备内存分配大小为1610612736失败。
ggml_vulkan: vk::Device::allocateMemory: ErrorOutOfDeviceMemory
可能是因为计算机没有足够的RAM来运行程序。
lxkprmvk7#
感谢@Lilicogamer13@warren-lei,在更换到较小的模型(OpenELM)后，现在终于可以正常工作了：)