Run Qwen1.5-1.8B on MTL iGPU with llama.cpp using ipex-llm backend and get no results
Closed this issue · 4 comments
violet17 commented
Follow guide: https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/llama_cpp_quickstart.html
command:
main.exe -m "C:\Users\admin\Desktop\ipex\llama-cpp\llama-cpp\libs\models\qwen1_5-1_8b-chat-q5_k_m.gguf" -n 512 --prompt "我的问题是：什么是零售？请把回答限制在五 十个汉字以内。" -t 8 -e -ngl 33 --color --no-mmap --temp 0
log:
(cpp) C:\Users\admin\Desktop\cpp>main.exe -m "C:\Users\admin\Desktop\ipex\llama-cpp\llama-cpp\libs\models\qwen1_5-1_8b-chat-q5_k_m.gguf" -n 512 --prompt "请基于```内的 内容回答。```Context:问题是：商品 攀升现象的盛行说明了什么？答案是:商品 攀升现象的盛行说明不同类型零售商之间的竞争加剧。Context:问题是：零售竞争如何体现？答案是:垄断竞争。Context:问题是：什么 是零售业态？答案是:零售业态是指零售企业为满足不同的消费者需求而形成的不同的经营形态，例如百货商店、折扣商店、仓库商店等 。```我的问题是：什么是多渠道零售？请把回答限制在五 十个汉字以内。" -t 8 -e -ngl 999 --color
Log start
main: build = 1 (c26dd9e)
main: built with IntelLLVM 2024.0.0 for
main: seed = 1715406086
llama_model_loader: loaded meta data with 21 key-value pairs and 291 tensors from C:\Users\admin\Desktop\ipex\llama-cpp\llama-cpp\libs\models\qwen1_5-1_8b-chat-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 = qwen2
llama_model_loader: - kv 1: general.name str = Qwen1.5-1.8B-Chat-AWQ-fp16
llama_model_loader: - kv 2: qwen2.block_count u32 = 24
llama_model_loader: - kv 3: qwen2.context_length u32 = 32768
llama_model_loader: - kv 4: qwen2.embedding_length u32 = 2048
llama_model_loader: - kv 5: qwen2.feed_forward_length u32 = 5504
llama_model_loader: - kv 6: qwen2.attention.head_count u32 = 16
llama_model_loader: - kv 7: qwen2.attention.head_count_kv u32 = 16
llama_model_loader: - kv 8: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 9: qwen2.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 10: qwen2.use_parallel_residual bool = true
llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 12: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 13: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 14: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 15: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 16: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 18: tokenizer.chat_template str = {% for message in messages %}{{'<|im_...
llama_model_loader: - kv 19: general.quantization_version u32 = 2
llama_model_loader: - kv 20: general.file_type u32 = 17
llama_model_loader: - type f32: 121 tensors
llama_model_loader: - type q5_1: 12 tensors
llama_model_loader: - type q8_0: 12 tensors
llama_model_loader: - type q5_K: 133 tensors
llama_model_loader: - type q6_K: 13 tensors
llm_load_vocab: missing pre-tokenizer type, using: 'default'
llm_load_vocab:
llm_load_vocab: ************************************
llm_load_vocab: GENERATION QUALITY WILL BE DEGRADED!
llm_load_vocab: CONSIDER REGENERATING THE MODEL
llm_load_vocab: ************************************
llm_load_vocab:
llm_load_vocab: special tokens definition check successful ( 293/151936 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = qwen2
llm_load_print_meta: vocab type = BPE
llm_load_print_meta: n_vocab = 151936
llm_load_print_meta: n_merges = 151387
llm_load_print_meta: n_ctx_train = 32768
llm_load_print_meta: n_embd = 2048
llm_load_print_meta: n_head = 16
llm_load_print_meta: n_head_kv = 16
llm_load_print_meta: n_layer = 24
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 = 1
llm_load_print_meta: n_embd_k_gqa = 2048
llm_load_print_meta: n_embd_v_gqa = 2048
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-06
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 = 5504
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 = 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 = 1B
llm_load_print_meta: model ftype = Q5_K - Medium
llm_load_print_meta: model params = 1.84 B
llm_load_print_meta: model size = 1.28 GiB (5.97 BPW)
llm_load_print_meta: general.name = Qwen1.5-1.8B-Chat-AWQ-fp16
llm_load_print_meta: BOS token = 151643 '<|endoftext|>'
llm_load_print_meta: EOS token = 151645 '<|im_end|>'
llm_load_print_meta: PAD token = 151643 '<|endoftext|>'
llm_load_print_meta: LF token = 148848 'ÄĬ'
llm_load_print_meta: EOT token = 151645 '<|im_end|>'
[SYCL] call ggml_init_sycl
ggml_init_sycl: GGML_SYCL_DEBUG: 0
ggml_init_sycl: GGML_SYCL_F16: no
found 1 SYCL devices:
| | | | |Max | |Max |Global | |
| | | | |compute|Max work|sub |mem | |
|ID| Device Type| Name|Version|units |group |group|size | Driver version|
|--|-------------------|---------------------------------------|-------|-------|--------|-----|-------|---------------------|
| 0| [level_zero:gpu:0]| Intel Arc Graphics| 1.3| 128| 1024| 32| 7446M| 1.3.28328|
ggml_backend_sycl_set_mul_device_mode: true
detect 1 SYCL GPUs: [0] with top Max compute units:128
llm_load_tensors: ggml ctx size = 0.28 MiB
llm_load_tensors: offloading 24 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 25/25 layers to GPU
llm_load_tensors: SYCL0 buffer size = 1103.31 MiB
llm_load_tensors: CPU buffer size = 204.02 MiB
....................................................................
llama_new_context_with_model: n_ctx = 512
llama_new_context_with_model: n_batch = 512
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: SYCL0 KV buffer size = 96.00 MiB
llama_new_context_with_model: KV self size = 96.00 MiB, K (f16): 48.00 MiB, V (f16): 48.00 MiB
llama_new_context_with_model: SYCL_Host output buffer size = 0.58 MiB
llama_new_context_with_model: SYCL0 compute buffer size = 300.75 MiB
llama_new_context_with_model: SYCL_Host compute buffer size = 5.01 MiB
llama_new_context_with_model: graph nodes = 870
llama_new_context_with_model: graph splits = 2
system_info: n_threads = 8 / 22 | 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 = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 |
CPU： MTL Ultra 7 165HL
GPU version: 5333 or 5448
version:
ipex-llm: 2.1.0b20240510
Could you please take a look on this issue？ Thanks.
rnwang04 commented
After offline sync with @violet17 , we found this issue only happens with Chinese prompt.
Apply below setting can solve this issue:
jason-dai commented
After offline sync with @violet17 , we found this issue only happens with Chinese prompt. Apply below setting can solve this issue:
Maybe also update the quickstart?
rnwang04 commented
Maybe also update the quickstart?
Ok, I will do it.