PowerInfer_AMD_Debug_Log
Apr 5, 2024
36 minutes
Environment:
aupxtx@aupxtx:~$ python3 -m torch.utils.collect_env
Collecting environment information...
PyTorch version: 2.3.0+rocm5.7
Is debug build: False
CUDA used to build PyTorch: N/A
ROCM used to build PyTorch: 5.7.31921-d1770ee1b
OS: Ubuntu 22.04.3 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: 17.0.0 (https://github.com/RadeonOpenCompute/llvm-project roc-6.0.2 24012 af27734ed982b52a9f1be0f035ac91726fc697e4)
CMake version: version 3.22.1
Libc version: glibc-2.35
Python version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-6.2.0-26-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: Radeon RX 7900 XTX (gfx1100)
Nvidia driver version: Could not collect
cuDNN version: Could not collect
HIP runtime version: 5.7.31921
MIOpen runtime version: 2.20.0
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 48 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 16
On-line CPU(s) list: 0-15
Vendor ID: AuthenticAMD
Model name: AMD Ryzen 7 7800X3D 8-Core Processor
CPU family: 25
Model: 97
Thread(s) per core: 2
Core(s) per socket: 8
Socket(s): 1
Stepping: 2
Frequency boost: enabled
CPU max MHz: 5049.0229
CPU min MHz: 3000.0000
BogoMIPS: 8399.69
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif x2avic v_spec_ctrl avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid overflow_recov succor smca fsrm flush_l1d
Virtualization: AMD-V
L1d cache: 256 KiB (8 instances)
L1i cache: 256 KiB (8 instances)
L2 cache: 8 MiB (8 instances)
L3 cache: 96 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-15
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] numpy==1.26.3
[pip3] pytorch-triton-rocm==2.3.0
[pip3] torch==2.3.0+rocm5.7
[pip3] torchaudio==2.3.0+rocm5.7
[pip3] torchvision==0.18.0+rocm5.7
Debug Log
1. Fail to generate GPU split
.............................................
invoking powerinfer Python module to generate gpu split for 59036.48 MiB of VRAM
Traceback (most recent call last):
File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.8/runpy-py", line 87, in _run_code
exec(code, run_globals)
File "/home/xxx/.local/lib/python3.8/site-packages/powerinfer/__main__.py", line 5, in <module>
from .export_split import export_split
File "/home/xxx/.local/lib/python3.8/site-packages/powerinfer/export_split.py", line 50, in <module>
def export_split(activations_path: str, output_path: str, solved_list: list[int], vram_capacity: int):
TypeError: 'type' object is not subscriptable
l1m_load_gpu_split_with_budget: error: failed to generate gpu split
llm_load_gpu_split: error: failed to generate gpu split, an empty one will be used
offload_ffn_split: applying augmentation to model - please wait ...
................................ done (6.43 ms)
1lm_load_gpu_split: offloaded 0.00 MiB of FFN weights to GPU
llama_new_context_with_model: n_ctx = 512
llama_new_context_with_model: freq_base = 10000.0
llama new context with model: freq scale = 1
llama_kv_cache_init: offloading v cache to GPU
llama kv cache init: offloading k cache to GPU
llama kv cache init: VRAM kv self = 256.00 MB
11ama_new_context_with_model: kv self size = 256.00 MB
llama_build_graph: non-view tensors processed: 548/836
Initial Python version is 3.8.xx, which not satisfied with Pre-requisites.
Solution: Upgrade Python Version to 3.8+
2. Segmentation fault (core dumped)
llama_model_loader: - tensor 58: blk.29.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 59: blk.29.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 60: blk.30.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 61: blk.30.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 62: blk.31.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 63: blk.31.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: unknown type i32
llama_model_loader: - kv 0: general.architecture str
llama_model_loader: - kv 1: generic.gpu_index.block_count u32
llama_model_loader: - kv 2: split.vram_capacity u64
llama_model_loader: - type i32: 64 tensors
loaded gpu_idx, vram_required: 18367365120
load_gpu_idx_for_model: applying gpu_idx adapter from './ReluLLaMA-7B/llama-7b-relu.powerinfer.gguf.generated.gpuidx' - please wait ...
................................................................ done (0.75 ms)
offload_ffn_split: applying augmentation to model - please wait ...
Segmentation fault (core dumped)
Now this bug has been fixed! Please refer to https://github.com/SJTU-IPADS/PowerInfer/pull/139
Attempted solutions: Change cudaMemcpyToSymbol(dev_sparse_threshold, &sparse_pred_threshold, sizeof(float)) to cudaMemcpyToSymbol(&dev_sparse_threshold, &sparse_pred_threshold, sizeof(float)) But Bug 3 occur
3. CUDA error 13: invalid device symbol
llama_model_loader: - tensor 60: blk.30.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 61: blk.30.gpu_bucket i32 [ 1792, 1, 1, 1 ]
llama_model_loader: - tensor 62: blk.31.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 63: blk.31.gpu_bucket i32 [ 2048, 1, 1, 1 ]
llama_model_loader: unknown type i32
llama_model_loader: - kv 0: general.architecture str
llama_model_loader: - kv 1: generic.gpu_index.block_count u32
llama_model_loader: - kv 2: split.vram_capacity u64
llama_model_loader: - type i32: 64 tensors
loaded gpu_idx, vram_required: 2093465600
load_gpu_idx_for_model: applying gpu_idx adapter from './ReluLLaMA-7B/llama-7b-relu.powerinfer.gguf.generated.gpuidx' - please wait ...
................................................................ done (1.91 ms)
offload_ffn_split: applying augmentation to model - please wait ...
CUDA error 13 at /var/lib/jenkins/PowerInfer/ggml-cuda.cu:9440: invalid device symbol
current device: 0
Now this bug has been fixed! Please refer to https://github.com/SJTU-IPADS/PowerInfer/pull/139
4. CUDA error 303: shared object initialization failed
llama_model_loader: - tensor 60: blk.30.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 61: blk.30.gpu_bucket i32 [ 1792, 1, 1, 1 ]
llama_model_loader: - tensor 62: blk.31.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 63: blk.31.gpu_bucket i32 [ 2048, 1, 1, 1 ]
llama_model_loader: unknown type i32
llama_model_loader: - kv 0: general.architecture str
llama_model_loader: - kv 1: generic.gpu_index.block_count u32
llama_model_loader: - kv 2: split.vram_capacity u64
llama_model_loader: - type i32: 64 tensors
loaded gpu_idx, vram_required: 2093465600
load_gpu_idx_for_model: applying gpu_idx adapter from './ReluLLaMA-7B/llama-7b-relu.powerinfer.gguf.generated.gpuidx' - please wait ...
................................................................ done (1.81 ms)
offload_ffn_split: applying augmentation to model - please wait ...
................................ done (1764.28 ms)
llm_load_gpu_split: offloaded 1980.00 MiB of FFN weights to GPU
llama_new_context_with_model: n_ctx = 512
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: offloading v cache to GPU
llama_kv_cache_init: offloading k cache to GPU
llama_kv_cache_init: VRAM kv self = 256.00 MB
llama_new_context_with_model: kv self size = 256.00 MB
llama_build_graph: non-view tensors processed: 548/1028
llama_build_graph: ****************************************************************
llama_build_graph: not all non-view tensors have been processed with a callback
llama_build_graph: this can indicate an inefficiency in the graph implementation
llama_build_graph: build with LLAMA_OFFLOAD_DEBUG for more info
llama_build_graph: ref: https://github.com/ggerganov/llama.cpp/pull/3837
llama_build_graph: ****************************************************************
llama_new_context_with_model: compute buffer total size = 36.25 MB
llama_new_context_with_model: VRAM scratch buffer: 34.69 MB
llama_new_context_with_model: total VRAM used: 8210.20 MB (model: 5939.52 MB, context: 290.69 MB)
CUDA error 303 at /var/lib/jenkins/PowerInfer/ggml-cuda.cu:7877: shared object initialization failed
current device: 0
All kernel function can’t be launched correctly and all trap into CUDA error 303!!!!!
Solution: Add additional compilation options: -DAMDGPU_TARGETS=gfx1100 (Replace 1100 to your card architecture, you can get it by rocminfo)
What I can confirm is that the program has just finished executing the llama.cpp function:
struct llama_context * llama_new_context_with_model( struct llama_model * model, struct llama_context_params params) {
According to the correct log record, the program should run the llama.cpp function afterwards:
Const char * llama_print_system_info (void){
And between these two, according to the log, it jumps into ggml cuda.cu:
static void ggml_cuda_op_flatten(const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst, const ggml_cuda_op_flatten_t op) {
And in the function of ggml cuda.cu:
op(src0, src1, dst, src0_ddf, src1_ddf, dst_ddf, main_stream);
An error occurred during operation, resulting in CUDA error 303 at the end.
5. Segmentation fault (core dumped)
llama_model_loader: - tensor 60: blk.30.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 61: blk.30.gpu_bucket i32 [ 1792, 1, 1, 1 ]
llama_model_loader: - tensor 62: blk.31.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 63: blk.31.gpu_bucket i32 [ 2048, 1, 1, 1 ]
llama_model_loader: unknown type i32
llama_model_loader: - kv 0: general.architecture str
llama_model_loader: - kv 1: generic.gpu_index.block_count u32
llama_model_loader: - kv 2: split.vram_capacity u64
llama_model_loader: - type i32: 64 tensors
loaded gpu_idx, vram_required: 2093465600
load_gpu_idx_for_model: applying gpu_idx adapter from './ReluLLaMA-7B/llama-7b-relu.powerinfer.gguf.generated.gpuidx' - please wait ...
................................................................ done (1.76 ms)
offload_ffn_split: applying augmentation to model - please wait ...
................................ done (1744.70 ms)
llm_load_gpu_split: offloaded 1980.00 MiB of FFN weights to GPU
llama_new_context_with_model: n_ctx = 512
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: offloading v cache to GPU
llama_kv_cache_init: offloading k cache to GPU
llama_kv_cache_init: VRAM kv self = 256.00 MB
llama_new_context_with_model: kv self size = 256.00 MB
llama_build_graph: non-view tensors processed: 548/1028
llama_build_graph: ****************************************************************
llama_build_graph: not all non-view tensors have been processed with a callback
llama_build_graph: this can indicate an inefficiency in the graph implementation
llama_build_graph: build with LLAMA_OFFLOAD_DEBUG for more info
llama_build_graph: ref: https://github.com/ggerganov/llama.cpp/pull/3837
llama_build_graph: ****************************************************************
llama_new_context_with_model: compute buffer total size = 36.25 MB
llama_new_context_with_model: VRAM scratch buffer: 34.69 MB
llama_new_context_with_model: total VRAM used: 8210.20 MB (model: 5939.52 MB, context: 290.69 MB)
Segmentation fault (core dumped)
I add some label in the code and claim that program can finish function llama_new_context_with_model and haven’t get into function const char * llama_print_system_info(void). Except that, all CUDA function can be executed correctly.
llama_new_context_with_model: compute buffer total size = 36.25 MB
llama_new_context_with_model: VRAM scratch buffer: 34.69 MB
llama_new_context_with_model: total VRAM used: 8210.20 MB (model: 5939.52 MB, context: 290.69 MB)
111
222
Operation: ggml_cuda_op_rms_norm
Operation: ggml_cuda_op_mul
Operation: ggml_cuda_op_rope
Operation: ggml_cuda_op_rope
Operation: ggml_cuda_op_scale
Operation: ggml_cuda_op_add
add_finish
Operation: ggml_cuda_op_soft_max
Operation: ggml_cuda_op_add
add_finish
Operation: ggml_cuda_op_rms_norm
Operation: ggml_cuda_op_mul
Operation: ggml_cuda_op_relu
Operation: ggml_cuda_op_add
add_finish
Segmentation fault (core dumped)
Solution: Add an additional running command parameter: –reset-gpu-index (To avoid any stale cache.)
6. Finish
#How to run it correctly
rm -rf build
CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++ cmake -S . -B build -DLLAMA_HIPBLAS=ON -DAMDGPU_TARGETS=gfx1100
cmake --build build --config Release -j 24
./build/bin/main -m ./ReluLLaMA-7B/llama-7b-relu.powerinfer.gguf -n 128 -p "Once upon a time" --ignore-eos --seed 0 --top-k 1 --reset-gpu-index
An correct output just like the following:
root@5de7c34ac60d:/var/lib/jenkins/PowerInfer# ./build/bin/main -m ./ReluLLaMA-7B/llama-7b-relu.powerinfer.gguf -n 128 -t 1 -p "Once upon a time" --ignore-eos --seed 0 --top-k 1 --reset-gpu-index
Log start
main: build = 1572 (47e9d7e)
main: built with AMD clang version 17.0.0 (https://github.com/RadeonOpenCompute/llvm-project roc-6.0.0 23483 7208e8d15fbf218deb74483ea8c549c67ca4985e) for x86_64-unknown-linux-gnu
main: seed = 0
ggml_init_cublas: GGML_CUDA_FORCE_MMQ: no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 1 ROCm devices:
Device 0: Radeon RX 7900 XTX, compute capability 11.0
llama_model_loader: loaded meta data with 18 key-value pairs and 355 tensors from ./ReluLLaMA-7B/llama-7b-relu.powerinfer.gguf (version GGUF V3 (latest))
llama_model_loader: - tensor 0: token_embd.weight f16 [ 4096, 32000, 1, 1 ]
llama_model_loader: - tensor 1: blk.0.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 2: blk.0.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 3: blk.0.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 4: blk.0.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 5: blk.0.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 6: blk.0.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 7: blk.0.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 8: blk.0.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 9: blk.0.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 10: blk.1.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 11: blk.1.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 12: blk.1.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 13: blk.1.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 14: blk.1.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 15: blk.1.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 16: blk.1.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 17: blk.1.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 18: blk.1.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 19: blk.2.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 20: blk.2.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 21: blk.2.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 22: blk.2.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 23: blk.2.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 24: blk.2.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 25: blk.2.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 26: blk.2.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 27: blk.2.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 28: blk.3.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 29: blk.3.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 30: blk.3.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 31: blk.3.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 32: blk.3.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 33: blk.3.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 34: blk.3.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 35: blk.3.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 36: blk.3.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 37: blk.4.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 38: blk.4.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 39: blk.4.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 40: blk.4.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 41: blk.4.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 42: blk.4.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 43: blk.4.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 44: blk.4.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 45: blk.4.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 46: blk.5.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 47: blk.5.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 48: blk.5.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 49: blk.5.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 50: blk.5.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 51: blk.5.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 52: blk.5.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 53: blk.5.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 54: blk.5.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 55: blk.6.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 56: blk.6.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 57: blk.6.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 58: blk.6.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 59: blk.6.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 60: blk.6.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 61: blk.6.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 62: blk.6.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 63: blk.6.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 64: blk.7.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 65: blk.7.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 66: blk.7.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 67: blk.7.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 68: blk.7.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 69: blk.7.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 70: blk.7.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 71: blk.7.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 72: blk.7.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 73: blk.8.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 74: blk.8.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 75: blk.8.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 76: blk.8.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 77: blk.8.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 78: blk.8.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 79: blk.8.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 80: blk.8.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 81: blk.8.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 82: blk.9.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 83: blk.9.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 84: blk.9.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 85: blk.9.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 86: blk.9.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 87: blk.9.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 88: blk.9.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 89: blk.9.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 90: blk.9.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 91: blk.10.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 92: blk.10.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 93: blk.10.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 94: blk.10.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 95: blk.10.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 96: blk.10.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 97: blk.10.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 98: blk.10.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 99: blk.10.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 100: blk.11.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 101: blk.11.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 102: blk.11.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 103: blk.11.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 104: blk.11.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 105: blk.11.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 106: blk.11.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 107: blk.11.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 108: blk.11.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 109: blk.12.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 110: blk.12.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 111: blk.12.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 112: blk.12.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 113: blk.12.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 114: blk.12.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 115: blk.12.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 116: blk.12.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 117: blk.12.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 118: blk.13.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 119: blk.13.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 120: blk.13.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 121: blk.13.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 122: blk.13.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 123: blk.13.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 124: blk.13.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 125: blk.13.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 126: blk.13.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 127: blk.14.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 128: blk.14.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 129: blk.14.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 130: blk.14.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 131: blk.14.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 132: blk.14.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 133: blk.14.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 134: blk.14.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 135: blk.14.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 136: blk.15.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 137: blk.15.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 138: blk.15.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 139: blk.15.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 140: blk.15.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 141: blk.15.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 142: blk.15.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 143: blk.15.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 144: blk.15.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 145: blk.16.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 146: blk.16.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 147: blk.16.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 148: blk.16.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 149: blk.16.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 150: blk.16.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 151: blk.16.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 152: blk.16.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 153: blk.16.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 154: blk.17.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 155: blk.17.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 156: blk.17.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 157: blk.17.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 158: blk.17.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 159: blk.17.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 160: blk.17.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 161: blk.17.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 162: blk.17.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 163: blk.18.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 164: blk.18.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 165: blk.18.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 166: blk.18.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 167: blk.18.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 168: blk.18.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 169: blk.18.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 170: blk.18.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 171: blk.18.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 172: blk.19.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 173: blk.19.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 174: blk.19.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 175: blk.19.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 176: blk.19.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 177: blk.19.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 178: blk.19.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 179: blk.19.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 180: blk.19.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 181: blk.20.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 182: blk.20.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 183: blk.20.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 184: blk.20.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 185: blk.20.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 186: blk.20.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 187: blk.20.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 188: blk.20.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 189: blk.20.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 190: blk.21.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 191: blk.21.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 192: blk.21.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 193: blk.21.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 194: blk.21.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 195: blk.21.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 196: blk.21.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 197: blk.21.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 198: blk.21.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 199: blk.22.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 200: blk.22.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 201: blk.22.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 202: blk.22.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 203: blk.22.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 204: blk.22.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 205: blk.22.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 206: blk.22.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 207: blk.22.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 208: blk.23.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 209: blk.23.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 210: blk.23.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 211: blk.23.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 212: blk.23.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 213: blk.23.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 214: blk.23.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 215: blk.23.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 216: blk.23.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 217: blk.24.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 218: blk.24.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 219: blk.24.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 220: blk.24.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 221: blk.24.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 222: blk.24.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 223: blk.24.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 224: blk.24.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 225: blk.24.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 226: blk.25.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 227: blk.25.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 228: blk.25.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 229: blk.25.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 230: blk.25.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 231: blk.25.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 232: blk.25.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 233: blk.25.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 234: blk.25.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 235: blk.26.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 236: blk.26.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 237: blk.26.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 238: blk.26.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 239: blk.26.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 240: blk.26.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 241: blk.26.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 242: blk.26.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 243: blk.26.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 244: blk.27.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 245: blk.27.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 246: blk.27.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 247: blk.27.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 248: blk.27.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 249: blk.27.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 250: blk.27.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 251: blk.27.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 252: blk.27.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 253: blk.28.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 254: blk.28.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 255: blk.28.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 256: blk.28.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 257: blk.28.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 258: blk.28.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 259: blk.28.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 260: blk.28.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 261: blk.28.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 262: blk.29.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 263: blk.29.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 264: blk.29.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 265: blk.29.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 266: blk.29.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 267: blk.29.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 268: blk.29.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 269: blk.29.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 270: blk.29.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 271: blk.30.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 272: blk.30.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 273: blk.30.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 274: blk.30.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 275: blk.30.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 276: blk.30.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 277: blk.30.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 278: blk.30.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 279: blk.30.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 280: blk.31.attn_q.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 281: blk.31.attn_k.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 282: blk.31.attn_v.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 283: blk.31.attn_output.weight f16 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 284: blk.31.ffn_gate.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 285: blk.31.ffn_up.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 286: blk.31.ffn_down_t.weight f16 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 287: blk.31.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 288: blk.31.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 289: output_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 290: output.weight f16 [ 4096, 32000, 1, 1 ]
llama_model_loader: - tensor 291: blk.0.fc1.weight f16 [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 292: blk.0.fc2.weight f16 [ 1024, 11008, 1, 1 ]
llama_model_loader: - tensor 293: blk.1.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 294: blk.1.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 295: blk.2.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 296: blk.2.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 297: blk.3.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 298: blk.3.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 299: blk.4.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 300: blk.4.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 301: blk.5.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 302: blk.5.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 303: blk.6.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 304: blk.6.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 305: blk.7.fc1.weight f16 [ 4096, 1536, 1, 1 ]
llama_model_loader: - tensor 306: blk.7.fc2.weight f16 [ 1536, 11008, 1, 1 ]
llama_model_loader: - tensor 307: blk.8.fc1.weight f16 [ 4096, 1536, 1, 1 ]
llama_model_loader: - tensor 308: blk.8.fc2.weight f16 [ 1536, 11008, 1, 1 ]
llama_model_loader: - tensor 309: blk.9.fc1.weight f16 [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 310: blk.9.fc2.weight f16 [ 1024, 11008, 1, 1 ]
llama_model_loader: - tensor 311: blk.10.fc1.weight f16 [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 312: blk.10.fc2.weight f16 [ 1024, 11008, 1, 1 ]
llama_model_loader: - tensor 313: blk.11.fc1.weight f16 [ 4096, 1024, 1, 1 ]
llama_model_loader: - tensor 314: blk.11.fc2.weight f16 [ 1024, 11008, 1, 1 ]
llama_model_loader: - tensor 315: blk.12.fc1.weight f16 [ 4096, 1280, 1, 1 ]
llama_model_loader: - tensor 316: blk.12.fc2.weight f16 [ 1280, 11008, 1, 1 ]
llama_model_loader: - tensor 317: blk.13.fc1.weight f16 [ 4096, 1280, 1, 1 ]
llama_model_loader: - tensor 318: blk.13.fc2.weight f16 [ 1280, 11008, 1, 1 ]
llama_model_loader: - tensor 319: blk.14.fc1.weight f16 [ 4096, 1536, 1, 1 ]
llama_model_loader: - tensor 320: blk.14.fc2.weight f16 [ 1536, 11008, 1, 1 ]
llama_model_loader: - tensor 321: blk.15.fc1.weight f16 [ 4096, 1536, 1, 1 ]
llama_model_loader: - tensor 322: blk.15.fc2.weight f16 [ 1536, 11008, 1, 1 ]
llama_model_loader: - tensor 323: blk.16.fc1.weight f16 [ 4096, 1536, 1, 1 ]
llama_model_loader: - tensor 324: blk.16.fc2.weight f16 [ 1536, 11008, 1, 1 ]
llama_model_loader: - tensor 325: blk.17.fc1.weight f16 [ 4096, 1536, 1, 1 ]
llama_model_loader: - tensor 326: blk.17.fc2.weight f16 [ 1536, 11008, 1, 1 ]
llama_model_loader: - tensor 327: blk.18.fc1.weight f16 [ 4096, 1536, 1, 1 ]
llama_model_loader: - tensor 328: blk.18.fc2.weight f16 [ 1536, 11008, 1, 1 ]
llama_model_loader: - tensor 329: blk.19.fc1.weight f16 [ 4096, 1792, 1, 1 ]
llama_model_loader: - tensor 330: blk.19.fc2.weight f16 [ 1792, 11008, 1, 1 ]
llama_model_loader: - tensor 331: blk.20.fc1.weight f16 [ 4096, 1792, 1, 1 ]
llama_model_loader: - tensor 332: blk.20.fc2.weight f16 [ 1792, 11008, 1, 1 ]
llama_model_loader: - tensor 333: blk.21.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 334: blk.21.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 335: blk.22.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 336: blk.22.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 337: blk.23.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 338: blk.23.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 339: blk.24.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 340: blk.24.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 341: blk.25.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 342: blk.25.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 343: blk.26.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 344: blk.26.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 345: blk.27.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 346: blk.27.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 347: blk.28.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 348: blk.28.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 349: blk.29.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 350: blk.29.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 351: blk.30.fc1.weight f16 [ 4096, 2048, 1, 1 ]
llama_model_loader: - tensor 352: blk.30.fc2.weight f16 [ 2048, 11008, 1, 1 ]
llama_model_loader: - tensor 353: blk.31.fc1.weight f16 [ 4096, 1536, 1, 1 ]
llama_model_loader: - tensor 354: blk.31.fc2.weight f16 [ 1536, 11008, 1, 1 ]
llama_model_loader: - kv 0: general.architecture str
llama_model_loader: - kv 1: general.name str
llama_model_loader: - kv 2: llama.context_length u32
llama_model_loader: - kv 3: llama.embedding_length u32
llama_model_loader: - kv 4: llama.block_count u32
llama_model_loader: - kv 5: llama.feed_forward_length u32
llama_model_loader: - kv 6: llama.rope.dimension_count u32
llama_model_loader: - kv 7: llama.attention.head_count u32
llama_model_loader: - kv 8: llama.attention.head_count_kv u32
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32
llama_model_loader: - kv 10: general.file_type u32
llama_model_loader: - kv 11: tokenizer.ggml.model str
llama_model_loader: - kv 12: tokenizer.ggml.tokens arr
llama_model_loader: - kv 13: tokenizer.ggml.scores arr
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr
llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32
llama_model_loader: - kv 17: tokenizer.ggml.padding_token_id u32
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type f16: 290 tensors
llama_model_load: PowerInfer model loaded. Sparse inference will be used.
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 = 2048
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 32
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_gqa = 1
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 = 11008
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_yarn_orig_ctx = 2048
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: model type = 7B
llm_load_print_meta: model ftype = mostly F16
llm_load_print_meta: model params = 7.57 B
llm_load_print_meta: model size = 14.11 GiB (16.00 BPW)
llm_load_print_meta: general.name = syx
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_print_meta: sparse_pred_threshold = 0.00
llm_load_sparse_model_tensors: ggml ctx size = 0.13 MB
llm_load_sparse_model_tensors: using ROCm for GPU acceleration
llm_load_sparse_model_tensors: offloaded layers from VRAM budget(24853348352 bytes): 33/32
llm_load_sparse_model_tensors: mem required = 14446.15 MB
llm_load_sparse_model_tensors: VRAM used: 5939.52 MB
....................................................................................................
invoking powerinfer Python module to generate gpu split for 17506.48 MiB of VRAM
llama_model_loader: loaded meta data with 3 key-value pairs and 64 tensors from ./ReluLLaMA-7B/llama-7b-relu.powerinfer.gguf.generated.gpuidx (version GGUF V3 (latest))
llama_model_loader: - tensor 0: blk.0.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 1: blk.0.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 2: blk.1.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 3: blk.1.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 4: blk.2.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 5: blk.2.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 6: blk.3.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 7: blk.3.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 8: blk.4.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 9: blk.4.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 10: blk.5.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 11: blk.5.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 12: blk.6.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 13: blk.6.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 14: blk.7.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 15: blk.7.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 16: blk.8.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 17: blk.8.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 18: blk.9.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 19: blk.9.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 20: blk.10.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 21: blk.10.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 22: blk.11.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 23: blk.11.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 24: blk.12.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 25: blk.12.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 26: blk.13.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 27: blk.13.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 28: blk.14.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 29: blk.14.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 30: blk.15.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 31: blk.15.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 32: blk.16.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 33: blk.16.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 34: blk.17.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 35: blk.17.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 36: blk.18.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 37: blk.18.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 38: blk.19.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 39: blk.19.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 40: blk.20.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 41: blk.20.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 42: blk.21.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 43: blk.21.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 44: blk.22.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 45: blk.22.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 46: blk.23.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 47: blk.23.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 48: blk.24.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 49: blk.24.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 50: blk.25.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 51: blk.25.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 52: blk.26.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 53: blk.26.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 54: blk.27.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 55: blk.27.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 56: blk.28.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 57: blk.28.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 58: blk.29.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 59: blk.29.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 60: blk.30.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 61: blk.30.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 62: blk.31.gpu_idx i32 [ 11008, 1, 1, 1 ]
llama_model_loader: - tensor 63: blk.31.gpu_bucket i32 [ 11008, 1, 1, 1 ]
llama_model_loader: unknown type i32
llama_model_loader: - kv 0: general.architecture str
llama_model_loader: - kv 1: generic.gpu_index.block_count u32
llama_model_loader: - kv 2: split.vram_capacity u64
llama_model_loader: - type i32: 64 tensors
load_gpu_idx_for_model: applying gpu_idx adapter from './ReluLLaMA-7B/llama-7b-relu.powerinfer.gguf.generated.gpuidx' - please wait ...
................................................................ done (0.75 ms)
offload_ffn_split: applying augmentation to model - please wait ...
................................ done (659.27 ms)
llm_load_gpu_split: offloaded 8256.00 MiB of FFN weights to GPU
llama_new_context_with_model: n_ctx = 512
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: offloading v cache to GPU
llama_kv_cache_init: offloading k cache to GPU
llama_kv_cache_init: VRAM kv self = 256.00 MB
llama_new_context_with_model: kv self size = 256.00 MB
llama_build_graph: non-view tensors processed: 580/836
llama_build_graph: ****************************************************************
llama_build_graph: not all non-view tensors have been processed with a callback
llama_build_graph: this can indicate an inefficiency in the graph implementation
llama_build_graph: build with LLAMA_OFFLOAD_DEBUG for more info
llama_build_graph: ref: https://github.com/ggerganov/llama.cpp/pull/3837
llama_build_graph: ****************************************************************
llama_new_context_with_model: compute buffer total size = 6.91 MB
llama_new_context_with_model: VRAM scratch buffer: 5.34 MB
llama_new_context_with_model: total VRAM used: 22712.86 MB (model: 14195.52 MB, context: 261.34 MB)
system_info: n_threads = 1 / 24 | AVX = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 |
sampling:
repeat_last_n = 64, repeat_penalty = 1.100, frequency_penalty = 0.000, presence_penalty = 0.000
top_k = 1, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800
mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
generate: n_ctx = 512, n_batch = 32, n_predict = 128, n_keep = 0
llama_print_timings: load time = 2472.15 ms
llama_print_timings: sample time = 10.74 ms / 128 runs ( 0.08 ms per token, 11916.95 tokens per second)
llama_print_timings: prompt eval time = 81.02 ms / 5 tokens ( 16.20 ms per token, 61.71 tokens per second)
llama_print_timings: eval time = 4574.03 ms / 127 runs ( 36.02 ms per token, 27.77 tokens per second)
llama_print_timings: total time = 4679.75 ms
Log end