Skip to content

Instantly share code, notes, and snippets.

@miminashi
Created August 9, 2025 23:43
Show Gist options
  • Select an option

  • Save miminashi/2b89b4ef22be598454dc571ed980f1bb to your computer and use it in GitHub Desktop.

Select an option

Save miminashi/2b89b4ef22be598454dc571ed980f1bb to your computer and use it in GitHub Desktop.
ubuntu@mi25:~/llama.cpp (master) $ set -x
./build/bin/llama-perplexity --n-gpu-layers 100 --split-mode layer -m ~/.cache/llama.cpp/unsloth_gpt-oss-20b-GGUF_gpt-oss-20b-F16.gguf -f ~/polano.txt
printf '\n\n'
./build/bin/llama-perplexity --n-gpu-layers 100 --split-mode layer -m ~/.cache/llama.cpp/unsloth_gpt-oss-20b-GGUF_gpt-oss-20b-UD-Q8_K_XL.gguf -f ~/polano.txt
set +x
++ parse_git_branch
++ git branch --no-color
++ sed -e '/^[^*]/d' -e 's/* \(.*\)/ (\1)/'
+ ./build/bin/llama-perplexity --n-gpu-layers 100 --split-mode layer -m /home/ubuntu/.cache/llama.cpp/unsloth_gpt-oss-20b-GGUF_gpt-oss-20b-F16.gguf -f /home/ubuntu/polano.txt
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 4 ROCm devices:
Device 0: Radeon Instinct MI25, gfx900:xnack- (0x900), VMM: no, Wave Size: 64
Device 1: Radeon Instinct MI25, gfx900:xnack- (0x900), VMM: no, Wave Size: 64
Device 2: Radeon Instinct MI25, gfx900:xnack- (0x900), VMM: no, Wave Size: 64
Device 3: Radeon Instinct MI25, gfx900:xnack- (0x900), VMM: no, Wave Size: 64
build: 6112 (99acbc99) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
llama_model_load_from_file_impl: using device ROCm0 (Radeon Instinct MI25) - 16352 MiB free
llama_model_load_from_file_impl: using device ROCm1 (Radeon Instinct MI25) - 16352 MiB free
llama_model_load_from_file_impl: using device ROCm2 (Radeon Instinct MI25) - 16352 MiB free
llama_model_load_from_file_impl: using device ROCm3 (Radeon Instinct MI25) - 16352 MiB free
llama_model_loader: loaded meta data with 37 key-value pairs and 459 tensors from /home/ubuntu/.cache/llama.cpp/unsloth_gpt-oss-20b-GGUF_gpt-oss-20b-F16.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 = gpt-oss
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Gpt-Oss-20B
llama_model_loader: - kv 3: general.basename str = Gpt-Oss-20B
llama_model_loader: - kv 4: general.quantized_by str = Unsloth
llama_model_loader: - kv 5: general.size_label str = 20B
llama_model_loader: - kv 6: general.license str = apache-2.0
llama_model_loader: - kv 7: general.repo_url str = https://huggingface.co/unsloth
llama_model_loader: - kv 8: general.tags arr[str,2] = ["vllm", "text-generation"]
llama_model_loader: - kv 9: gpt-oss.block_count u32 = 24
llama_model_loader: - kv 10: gpt-oss.context_length u32 = 131072
llama_model_loader: - kv 11: gpt-oss.embedding_length u32 = 2880
llama_model_loader: - kv 12: gpt-oss.feed_forward_length u32 = 2880
llama_model_loader: - kv 13: gpt-oss.attention.head_count u32 = 64
llama_model_loader: - kv 14: gpt-oss.attention.head_count_kv u32 = 8
llama_model_loader: - kv 15: gpt-oss.rope.freq_base f32 = 150000.000000
llama_model_loader: - kv 16: gpt-oss.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 17: gpt-oss.expert_count u32 = 32
llama_model_loader: - kv 18: gpt-oss.expert_used_count u32 = 4
llama_model_loader: - kv 19: gpt-oss.attention.key_length u32 = 64
llama_model_loader: - kv 20: gpt-oss.attention.value_length u32 = 64
llama_model_loader: - kv 21: general.file_type u32 = 1
llama_model_loader: - kv 22: gpt-oss.attention.sliding_window u32 = 128
llama_model_loader: - kv 23: gpt-oss.expert_feed_forward_length u32 = 2880
llama_model_loader: - kv 24: gpt-oss.rope.scaling.type str = yarn
llama_model_loader: - kv 25: gpt-oss.rope.scaling.factor f32 = 32.000000
llama_model_loader: - kv 26: gpt-oss.rope.scaling.original_context_length u32 = 4096
llama_model_loader: - kv 27: general.quantization_version u32 = 2
llama_model_loader: - kv 28: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 29: tokenizer.ggml.pre str = gpt-4o
llama_model_loader: - kv 30: tokenizer.ggml.tokens arr[str,201088] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 31: tokenizer.ggml.token_type arr[i32,201088] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 32: tokenizer.ggml.merges arr[str,446189] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 33: tokenizer.ggml.bos_token_id u32 = 199998
llama_model_loader: - kv 34: tokenizer.ggml.eos_token_id u32 = 200002
llama_model_loader: - kv 35: tokenizer.ggml.padding_token_id u32 = 200017
llama_model_loader: - kv 36: tokenizer.chat_template str = {# Copyright 2025-present Unsloth. Ap...
llama_model_loader: - type f32: 289 tensors
llama_model_loader: - type f16: 98 tensors
llama_model_loader: - type mxfp4: 72 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = F16
print_info: file size = 12.83 GiB (5.27 BPW)
load: printing all EOG tokens:
load: - 199999 ('<|endoftext|>')
load: - 200002 ('<|return|>')
load: - 200007 ('<|end|>')
load: - 200012 ('<|call|>')
load: special_eog_ids contains both '<|return|>' and '<|call|>' tokens, removing '<|end|>' token from EOG list
load: special tokens cache size = 21
load: token to piece cache size = 1.3332 MB
print_info: arch = gpt-oss
print_info: vocab_only = 0
print_info: n_ctx_train = 131072
print_info: n_embd = 2880
print_info: n_layer = 24
print_info: n_head = 64
print_info: n_head_kv = 8
print_info: n_rot = 64
print_info: n_swa = 128
print_info: is_swa_any = 1
print_info: n_embd_head_k = 64
print_info: n_embd_head_v = 64
print_info: n_gqa = 8
print_info: n_embd_k_gqa = 512
print_info: n_embd_v_gqa = 512
print_info: f_norm_eps = 0.0e+00
print_info: f_norm_rms_eps = 1.0e-05
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 = 0.0e+00
print_info: n_ff = 2880
print_info: n_expert = 32
print_info: n_expert_used = 4
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = 2
print_info: rope scaling = yarn
print_info: freq_base_train = 150000.0
print_info: freq_scale_train = 0.03125
print_info: n_ctx_orig_yarn = 4096
print_info: rope_finetuned = unknown
print_info: model type = ?B
print_info: model params = 20.91 B
print_info: general.name = Gpt-Oss-20B
print_info: n_ff_exp = 2880
print_info: vocab type = BPE
print_info: n_vocab = 201088
print_info: n_merges = 446189
print_info: BOS token = 199998 '<|startoftext|>'
print_info: EOS token = 200002 '<|return|>'
print_info: EOT token = 199999 '<|endoftext|>'
print_info: PAD token = 200017 '<|reserved_200017|>'
print_info: LF token = 198 'Ċ'
print_info: EOG token = 199999 '<|endoftext|>'
print_info: EOG token = 200002 '<|return|>'
print_info: EOG token = 200012 '<|call|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 24 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 25/25 layers to GPU
load_tensors: ROCm0 model buffer size = 3188.52 MiB
load_tensors: ROCm1 model buffer size = 2733.01 MiB
load_tensors: ROCm2 model buffer size = 2733.01 MiB
load_tensors: ROCm3 model buffer size = 3382.13 MiB
load_tensors: CPU_Mapped model buffer size = 1104.61 MiB
...................................................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 4
llama_context: n_ctx = 2048
llama_context: n_ctx_per_seq = 512
llama_context: n_batch = 2048
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = 0
llama_context: kv_unified = false
llama_context: freq_base = 150000.0
llama_context: freq_scale = 0.03125
llama_context: n_ctx_per_seq (512) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_context: requested n_seq_max (4) > 1, but swa_full is not enabled -- performance may be degraded: https://github.com/ggml-org/llama.cpp/pull/13845#issuecomment-2924800573
llama_context: ROCm_Host output buffer size = 3.07 MiB
llama_kv_cache_unified_iswa: creating non-SWA KV cache, size = 512 cells
llama_kv_cache_unified: ROCm0 KV buffer size = 12.00 MiB
llama_kv_cache_unified: ROCm1 KV buffer size = 12.00 MiB
llama_kv_cache_unified: ROCm2 KV buffer size = 12.00 MiB
llama_kv_cache_unified: ROCm3 KV buffer size = 12.00 MiB
llama_kv_cache_unified: size = 48.00 MiB ( 512 cells, 12 layers, 4/4 seqs), K (f16): 24.00 MiB, V (f16): 24.00 MiB
llama_kv_cache_unified_iswa: creating SWA KV cache, size = 512 cells
llama_kv_cache_unified: ROCm0 KV buffer size = 16.00 MiB
llama_kv_cache_unified: ROCm1 KV buffer size = 12.00 MiB
llama_kv_cache_unified: ROCm2 KV buffer size = 12.00 MiB
llama_kv_cache_unified: ROCm3 KV buffer size = 8.00 MiB
llama_kv_cache_unified: size = 48.00 MiB ( 512 cells, 12 layers, 4/4 seqs), K (f16): 24.00 MiB, V (f16): 24.00 MiB
llama_context: pipeline parallelism enabled (n_copies=4)
llama_context: ROCm0 compute buffer size = 137.79 MiB
llama_context: ROCm1 compute buffer size = 137.79 MiB
llama_context: ROCm2 compute buffer size = 137.79 MiB
llama_context: ROCm3 compute buffer size = 444.92 MiB
llama_context: ROCm_Host compute buffer size = 29.68 MiB
llama_context: graph nodes = 1446
llama_context: graph splits = 5
common_init_from_params: added <|endoftext|> logit bias = -inf
common_init_from_params: added <|return|> logit bias = -inf
common_init_from_params: added <|call|> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 2048
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
system_info: n_threads = 12 (n_threads_batch = 12) / 24 | ROCm : NO_VMM = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 |
perplexity: tokenizing the input ..
perplexity: tokenization took 113.776 ms
perplexity: calculating perplexity over 70 chunks, n_ctx=512, batch_size=2048, n_seq=4
perplexity: 7.47 seconds per pass - ETA 2.17 minutes
[1]112.9391,[2]120.3856,[3]99.8193,[4]92.5444,[5]88.6741,[6]89.6368,[7]91.0741,[8]92.2524,[9]89.6240,[10]90.4831,[11]89.4148,[12]89.9362,[13]88.6410,[14]89.3298,[15]89.1087,[16]89.3652,[17]91.5408,[18]90.9635,[19]91.4515,[20]89.9630,[21]89.1542,[22]89.6232,[23]91.0604,[24]90.9767,[25]90.7946,[26]89.9260,[27]89.9649,[28]91.2270,[29]91.6070,[30]91.0361,[31]91.3673,[32]91.8827,[33]92.4371,[34]92.4308,[35]91.4885,[36]91.1588,[37]90.6893,[38]90.8425,[39]90.3654,[40]90.2084,[41]89.7867,[42]90.2956,[43]90.6560,[44]89.9171,[45]89.7907,[46]90.0890,[47]90.1316,[48]90.6154,[49]90.3287,[50]90.4228,[51]90.8813,[52]90.1366,[53]90.2139,[54]90.3047,[55]90.1718,[56]89.5759,[57]90.1230,[58]90.6507,[59]90.6380,[60]90.6367,[61]90.8753,[62]90.7443,[63]90.7123,[64]90.5564,[65]90.3993,[66]90.4221,[67]90.0149,[68]90.3950,[69]90.6447,[70]90.9716,
Final estimate: PPL = 90.9716 +/- 1.62124
llama_perf_context_print: load time = 6037.53 ms
llama_perf_context_print: prompt eval time = 104525.96 ms / 35840 tokens ( 2.92 ms per token, 342.88 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 109684.47 ms / 35841 tokens
llama_perf_context_print: graphs reused = 0
++ parse_git_branch
++ git branch --no-color
++ sed -e '/^[^*]/d' -e 's/* \(.*\)/ (\1)/'
+ printf '\n\n'
++ parse_git_branch
++ git branch --no-color
++ sed -e '/^[^*]/d' -e 's/* \(.*\)/ (\1)/'
+ ./build/bin/llama-perplexity --n-gpu-layers 100 --split-mode layer -m /home/ubuntu/.cache/llama.cpp/unsloth_gpt-oss-20b-GGUF_gpt-oss-20b-UD-Q8_K_XL.gguf -f /home/ubuntu/polano.txt
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 4 ROCm devices:
Device 0: Radeon Instinct MI25, gfx900:xnack- (0x900), VMM: no, Wave Size: 64
Device 1: Radeon Instinct MI25, gfx900:xnack- (0x900), VMM: no, Wave Size: 64
Device 2: Radeon Instinct MI25, gfx900:xnack- (0x900), VMM: no, Wave Size: 64
Device 3: Radeon Instinct MI25, gfx900:xnack- (0x900), VMM: no, Wave Size: 64
build: 6112 (99acbc99) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
llama_model_load_from_file_impl: using device ROCm0 (Radeon Instinct MI25) - 16352 MiB free
llama_model_load_from_file_impl: using device ROCm1 (Radeon Instinct MI25) - 16352 MiB free
llama_model_load_from_file_impl: using device ROCm2 (Radeon Instinct MI25) - 16352 MiB free
llama_model_load_from_file_impl: using device ROCm3 (Radeon Instinct MI25) - 16352 MiB free
llama_model_loader: loaded meta data with 37 key-value pairs and 459 tensors from /home/ubuntu/.cache/llama.cpp/unsloth_gpt-oss-20b-GGUF_gpt-oss-20b-UD-Q8_K_XL.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 = gpt-oss
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Gpt-Oss-20B
llama_model_loader: - kv 3: general.basename str = Gpt-Oss-20B
llama_model_loader: - kv 4: general.quantized_by str = Unsloth
llama_model_loader: - kv 5: general.size_label str = 20B
llama_model_loader: - kv 6: general.license str = apache-2.0
llama_model_loader: - kv 7: general.repo_url str = https://huggingface.co/unsloth
llama_model_loader: - kv 8: general.tags arr[str,2] = ["vllm", "text-generation"]
llama_model_loader: - kv 9: gpt-oss.block_count u32 = 24
llama_model_loader: - kv 10: gpt-oss.context_length u32 = 131072
llama_model_loader: - kv 11: gpt-oss.embedding_length u32 = 2880
llama_model_loader: - kv 12: gpt-oss.feed_forward_length u32 = 2880
llama_model_loader: - kv 13: gpt-oss.attention.head_count u32 = 64
llama_model_loader: - kv 14: gpt-oss.attention.head_count_kv u32 = 8
llama_model_loader: - kv 15: gpt-oss.rope.freq_base f32 = 150000.000000
llama_model_loader: - kv 16: gpt-oss.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 17: gpt-oss.expert_count u32 = 32
llama_model_loader: - kv 18: gpt-oss.expert_used_count u32 = 4
llama_model_loader: - kv 19: gpt-oss.attention.key_length u32 = 64
llama_model_loader: - kv 20: gpt-oss.attention.value_length u32 = 64
llama_model_loader: - kv 21: gpt-oss.attention.sliding_window u32 = 128
llama_model_loader: - kv 22: gpt-oss.expert_feed_forward_length u32 = 2880
llama_model_loader: - kv 23: gpt-oss.rope.scaling.type str = yarn
llama_model_loader: - kv 24: gpt-oss.rope.scaling.factor f32 = 32.000000
llama_model_loader: - kv 25: gpt-oss.rope.scaling.original_context_length u32 = 4096
llama_model_loader: - kv 26: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 27: tokenizer.ggml.pre str = gpt-4o
llama_model_loader: - kv 28: tokenizer.ggml.tokens arr[str,201088] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 29: tokenizer.ggml.token_type arr[i32,201088] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 30: tokenizer.ggml.merges arr[str,446189] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 31: tokenizer.ggml.bos_token_id u32 = 199998
llama_model_loader: - kv 32: tokenizer.ggml.eos_token_id u32 = 200002
llama_model_loader: - kv 33: tokenizer.ggml.padding_token_id u32 = 200017
llama_model_loader: - kv 34: tokenizer.chat_template str = {# Chat template fixes by Unsloth #}\n...
llama_model_loader: - kv 35: general.quantization_version u32 = 2
llama_model_loader: - kv 36: general.file_type u32 = 7
llama_model_loader: - type f32: 289 tensors
llama_model_loader: - type f16: 2 tensors
llama_model_loader: - type q8_0: 96 tensors
llama_model_loader: - type mxfp4: 72 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q8_0
print_info: file size = 12.28 GiB (5.04 BPW)
load: printing all EOG tokens:
load: - 199999 ('<|endoftext|>')
load: - 200002 ('<|return|>')
load: - 200007 ('<|end|>')
load: - 200012 ('<|call|>')
load: special_eog_ids contains both '<|return|>' and '<|call|>' tokens, removing '<|end|>' token from EOG list
load: special tokens cache size = 21
load: token to piece cache size = 1.3332 MB
print_info: arch = gpt-oss
print_info: vocab_only = 0
print_info: n_ctx_train = 131072
print_info: n_embd = 2880
print_info: n_layer = 24
print_info: n_head = 64
print_info: n_head_kv = 8
print_info: n_rot = 64
print_info: n_swa = 128
print_info: is_swa_any = 1
print_info: n_embd_head_k = 64
print_info: n_embd_head_v = 64
print_info: n_gqa = 8
print_info: n_embd_k_gqa = 512
print_info: n_embd_v_gqa = 512
print_info: f_norm_eps = 0.0e+00
print_info: f_norm_rms_eps = 1.0e-05
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 = 0.0e+00
print_info: n_ff = 2880
print_info: n_expert = 32
print_info: n_expert_used = 4
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = 2
print_info: rope scaling = yarn
print_info: freq_base_train = 150000.0
print_info: freq_scale_train = 0.03125
print_info: n_ctx_orig_yarn = 4096
print_info: rope_finetuned = unknown
print_info: model type = ?B
print_info: model params = 20.91 B
print_info: general.name = Gpt-Oss-20B
print_info: n_ff_exp = 2880
print_info: vocab type = BPE
print_info: n_vocab = 201088
print_info: n_merges = 446189
print_info: BOS token = 199998 '<|startoftext|>'
print_info: EOS token = 200002 '<|return|>'
print_info: EOT token = 199999 '<|endoftext|>'
print_info: PAD token = 200017 '<|reserved_200017|>'
print_info: LF token = 198 'Ċ'
print_info: EOG token = 199999 '<|endoftext|>'
print_info: EOG token = 200002 '<|return|>'
print_info: EOG token = 200012 '<|call|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 24 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 25/25 layers to GPU
load_tensors: ROCm0 model buffer size = 3022.41 MiB
load_tensors: ROCm1 model buffer size = 2590.64 MiB
load_tensors: ROCm2 model buffer size = 2590.64 MiB
load_tensors: ROCm3 model buffer size = 3263.48 MiB
load_tensors: CPU_Mapped model buffer size = 1104.61 MiB
...............................................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 4
llama_context: n_ctx = 2048
llama_context: n_ctx_per_seq = 512
llama_context: n_batch = 2048
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = 0
llama_context: kv_unified = false
llama_context: freq_base = 150000.0
llama_context: freq_scale = 0.03125
llama_context: n_ctx_per_seq (512) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_context: requested n_seq_max (4) > 1, but swa_full is not enabled -- performance may be degraded: https://github.com/ggml-org/llama.cpp/pull/13845#issuecomment-2924800573
llama_context: ROCm_Host output buffer size = 3.07 MiB
llama_kv_cache_unified_iswa: creating non-SWA KV cache, size = 512 cells
llama_kv_cache_unified: ROCm0 KV buffer size = 12.00 MiB
llama_kv_cache_unified: ROCm1 KV buffer size = 12.00 MiB
llama_kv_cache_unified: ROCm2 KV buffer size = 12.00 MiB
llama_kv_cache_unified: ROCm3 KV buffer size = 12.00 MiB
llama_kv_cache_unified: size = 48.00 MiB ( 512 cells, 12 layers, 4/4 seqs), K (f16): 24.00 MiB, V (f16): 24.00 MiB
llama_kv_cache_unified_iswa: creating SWA KV cache, size = 512 cells
llama_kv_cache_unified: ROCm0 KV buffer size = 16.00 MiB
llama_kv_cache_unified: ROCm1 KV buffer size = 12.00 MiB
llama_kv_cache_unified: ROCm2 KV buffer size = 12.00 MiB
llama_kv_cache_unified: ROCm3 KV buffer size = 8.00 MiB
llama_kv_cache_unified: size = 48.00 MiB ( 512 cells, 12 layers, 4/4 seqs), K (f16): 24.00 MiB, V (f16): 24.00 MiB
llama_context: pipeline parallelism enabled (n_copies=4)
llama_context: ROCm0 compute buffer size = 137.79 MiB
llama_context: ROCm1 compute buffer size = 137.79 MiB
llama_context: ROCm2 compute buffer size = 137.79 MiB
llama_context: ROCm3 compute buffer size = 444.92 MiB
llama_context: ROCm_Host compute buffer size = 29.68 MiB
llama_context: graph nodes = 1446
llama_context: graph splits = 5
common_init_from_params: added <|endoftext|> logit bias = -inf
common_init_from_params: added <|return|> logit bias = -inf
common_init_from_params: added <|call|> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 2048
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
system_info: n_threads = 12 (n_threads_batch = 12) / 24 | ROCm : NO_VMM = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 |
perplexity: tokenizing the input ..
perplexity: tokenization took 113.672 ms
perplexity: calculating perplexity over 70 chunks, n_ctx=512, batch_size=2048, n_seq=4
perplexity: 8.07 seconds per pass - ETA 2.35 minutes
[1]115.0262,[2]122.7098,[3]100.3466,[4]93.4961,[5]89.6047,[6]90.0965,[7]91.8012,[8]92.3142,[9]89.6770,[10]90.7297,[11]89.6987,[12]90.3249,[13]89.0910,[14]89.6744,[15]89.5042,[16]90.0630,[17]92.1337,[18]91.7380,[19]92.3333,[20]90.6335,[21]89.8392,[22]90.2258,[23]91.5899,[24]91.4898,[25]91.1945,[26]90.3981,[27]90.5297,[28]91.5912,[29]91.9983,[30]91.4049,[31]91.8051,[32]92.0515,[33]92.5888,[34]92.5595,[35]91.5543,[36]91.2818,[37]90.8417,[38]90.9532,[39]90.4572,[40]90.3260,[41]89.9503,[42]90.4023,[43]90.8267,[44]90.1623,[45]90.0122,[46]90.2988,[47]90.3504,[48]90.8263,[49]90.6357,[50]90.6904,[51]91.1480,[52]90.4410,[53]90.5445,[54]90.6409,[55]90.5900,[56]90.0046,[57]90.4890,[58]90.9705,[59]90.9032,[60]90.8509,[61]91.1024,[62]90.9639,[63]90.9586,[64]90.7712,[65]90.6252,[66]90.6669,[67]90.2588,[68]90.6704,[69]90.8999,[70]91.1773,
Final estimate: PPL = 91.1773 +/- 1.62520
llama_perf_context_print: load time = 5565.62 ms
llama_perf_context_print: prompt eval time = 117138.47 ms / 35840 tokens ( 3.27 ms per token, 305.96 tokens per second)
llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_perf_context_print: total time = 122369.80 ms / 35841 tokens
llama_perf_context_print: graphs reused = 0
++ parse_git_branch
++ git branch --no-color
++ sed -e '/^[^*]/d' -e 's/* \(.*\)/ (\1)/'
+ set +x
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment