Open
Description
Name and Version
.\build\bin\Release\llama-server.exe --version
version: 5561 (8726392)
built with MSVC 19.43.34810.0 for x64
Operating systems
Windows
Which llama.cpp modules do you know to be affected?
llama-server
Command line
.\build\bin\Release\llama-server.exe -m D:\huggingface\hub\models--unsloth--gemma-3-27b-it-GGUF\snapshots\b7609a0532f5be7a679ace6a6ea3382e0ac3228c\gemma-3-27b-it-UD-Q6_K_XL.gguf -md D:\huggingface\hub\models--unsloth--gemma-3-4b-it-GGUF\snapshots\837fb61240cea4985fd23bc904284ee38dd47c1c\gemma-3-4b-it-UD-Q2_K_XL.gguf --flash-attn -ngl 999 -ngld 999 --tensor-split 1,1 --ctx-size 131072Problem description & steps to reproduce
Apologies, I don't know if this is user error, system error, or software error. Running llama-server with Gemma 3 27b UD Q6_K_XL as main and Gemma 3 4b UD Q2_K_XL as draft. I've tried different variations of both and get the same problem.
I have a dual 3090 setup in Windows. Sending queries fails with the error "get_logits_ith: invalid logits id 0, reason: batch.logits[0] != true". Sometimes the system will run successfully for some number of queries before failing.
I also see a number of warnings(?) like "decode: failed to find KV cache slot for batch of size 10", and significantly reducing the context length and reducing the defrag-thold doesn't reduce their frequency.
Note Gemma 3 27b runs fine without these issues without using a draft model.
First Bad Commit
No response
Relevant log output
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 2 CUDA devices:
Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
Device 1: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
build: 5561 (8726392d) with MSVC 19.43.34810.0 for x64
system info: n_threads = 12, n_threads_batch = 12, total_threads = 24
system_info: n_threads = 12 (n_threads_batch = 12) / 24 | CUDA : ARCHS = 860 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | OPENMP = 1 | AARCH64_REPACK = 1 |
main: binding port with default address family
main: HTTP server is listening, hostname: 127.0.0.1, port: 8080, http threads: 23
main: loading model
srv load_model: loading model 'D:\huggingface\hub\models--unsloth--gemma-3-27b-it-GGUF\snapshots\b7609a0532f5be7a679ace6a6ea3382e0ac3228c\gemma-3-27b-it-UD-Q6_K_XL.gguf'
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3090) - 23306 MiB free
llama_model_load_from_file_impl: using device CUDA1 (NVIDIA GeForce RTX 3090) - 23306 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 808 tensors from D:\huggingface\hub\models--unsloth--gemma-3-27b-it-GGUF\snapshots\b7609a0532f5be7a679ace6a6ea3382e0ac3228c\gemma-3-27b-it-UD-Q6_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 = gemma3
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Gemma-3-27B-It
llama_model_loader: - kv 3: general.finetune str = it
llama_model_loader: - kv 4: general.basename str = Gemma-3-27B-It
llama_model_loader: - kv 5: general.quantized_by str = Unsloth
llama_model_loader: - kv 6: general.size_label str = 27B
llama_model_loader: - kv 7: general.repo_url str = https://huggingface.co/unsloth
llama_model_loader: - kv 8: gemma3.context_length u32 = 131072
llama_model_loader: - kv 9: gemma3.embedding_length u32 = 5376
llama_model_loader: - kv 10: gemma3.block_count u32 = 62
llama_model_loader: - kv 11: gemma3.feed_forward_length u32 = 21504
llama_model_loader: - kv 12: gemma3.attention.head_count u32 = 32
llama_model_loader: - kv 13: gemma3.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 14: gemma3.attention.key_length u32 = 128
llama_model_loader: - kv 15: gemma3.attention.value_length u32 = 128
llama_model_loader: - kv 16: gemma3.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 17: gemma3.attention.sliding_window u32 = 1024
llama_model_loader: - kv 18: gemma3.attention.head_count_kv u32 = 16
llama_model_loader: - kv 19: gemma3.rope.scaling.type str = linear
llama_model_loader: - kv 20: gemma3.rope.scaling.factor f32 = 8.000000
llama_model_loader: - kv 21: tokenizer.ggml.model str = llama
llama_model_loader: - kv 22: tokenizer.ggml.pre str = default
llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,262208] = ["<pad>", "<eos>", "<bos>", "<unk>", ...
llama_model_loader: - kv 24: tokenizer.ggml.scores arr[f32,262208] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 25: tokenizer.ggml.token_type arr[i32,262208] = [3, 3, 3, 3, 3, 4, 3, 3, 3, 3, 3, 3, ...
llama_model_loader: - kv 26: tokenizer.ggml.bos_token_id u32 = 2
llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 106
llama_model_loader: - kv 28: tokenizer.ggml.unknown_token_id u32 = 3
llama_model_loader: - kv 29: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 30: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 32: tokenizer.chat_template str = {{ bos_token }}\n{%- if messages[0]['r...
llama_model_loader: - kv 33: tokenizer.ggml.add_space_prefix bool = false
llama_model_loader: - kv 34: general.quantization_version u32 = 2
llama_model_loader: - kv 35: general.file_type u32 = 18
llama_model_loader: - kv 36: quantize.imatrix.file str = gemma-3-27b-it-GGUF/imatrix_unsloth.dat
llama_model_loader: - kv 37: quantize.imatrix.dataset str = unsloth_calibration_gemma-3-27b-it.txt
llama_model_loader: - kv 38: quantize.imatrix.entries_count i32 = 434
llama_model_loader: - kv 39: quantize.imatrix.chunks_count i32 = 663
llama_model_loader: - type f32: 373 tensors
llama_model_loader: - type q8_0: 207 tensors
llama_model_loader: - type q6_K: 228 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q6_K
print_info: file size = 22.09 GiB (7.03 BPW)
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 = 5376
print_info: n_layer = 62
print_info: n_head = 32
print_info: n_head_kv = 16
print_info: n_rot = 128
print_info: n_swa = 1024
print_info: is_swa_any = 1
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 2
print_info: n_embd_k_gqa = 2048
print_info: n_embd_v_gqa = 2048
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 = 7.7e-02
print_info: n_ff = 21504
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: ssm_d_conv = 0
print_info: ssm_d_inner = 0
print_info: ssm_d_state = 0
print_info: ssm_dt_rank = 0
print_info: ssm_dt_b_c_rms = 0
print_info: model type = 27B
print_info: model params = 27.01 B
print_info: general.name = Gemma-3-27B-It
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 = 106 '<end_of_turn>'
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 = 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 62 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 63/63 layers to GPU
load_tensors: CUDA0 model buffer size = 11011.26 MiB
load_tensors: CUDA1 model buffer size = 11612.91 MiB
load_tensors: CPU_Mapped model buffer size = 1428.35 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 = 1
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_unified_iswa: creating non-SWA KV cache, size = 131072 cells
llama_kv_cache_unified: CUDA0 KV buffer size = 5120.00 MiB
llama_kv_cache_unified: CUDA1 KV buffer size = 5120.00 MiB
llama_kv_cache_unified: size = 10240.00 MiB (131072 cells, 10 layers, 1 seqs), K (f16): 5120.00 MiB, V (f16): 5120.00 MiB
llama_kv_cache_unified_iswa: creating SWA KV cache, size = 1536 cells
llama_kv_cache_unified: CUDA0 KV buffer size = 324.00 MiB
llama_kv_cache_unified: CUDA1 KV buffer size = 300.00 MiB
llama_kv_cache_unified: size = 624.00 MiB ( 1536 cells, 52 layers, 1 seqs), K (f16): 312.00 MiB, V (f16): 312.00 MiB
llama_context: pipeline parallelism enabled (n_copies=4)
llama_context: CUDA0 compute buffer size = 1328.51 MiB
llama_context: CUDA1 compute buffer size = 1124.64 MiB
llama_context: CUDA_Host compute buffer size = 1046.52 MiB
llama_context: graph nodes = 2489
llama_context: graph splits = 3
common_init_from_params: KV cache shifting is not supported for this context, disabling KV cache shifting
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)
srv load_model: loading draft model 'D:\huggingface\hub\models--unsloth--gemma-3-4b-it-GGUF\snapshots\837fb61240cea4985fd23bc904284ee38dd47c1c\gemma-3-4b-it-UD-Q2_K_XL.gguf'
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3090) - 5484 MiB free
llama_model_load_from_file_impl: using device CUDA1 (NVIDIA GeForce RTX 3090) - 4604 MiB free
llama_model_loader: loaded meta data with 40 key-value pairs and 444 tensors from D:\huggingface\hub\models--unsloth--gemma-3-4b-it-GGUF\snapshots\837fb61240cea4985fd23bc904284ee38dd47c1c\gemma-3-4b-it-UD-Q2_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 = gemma3
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Gemma-3-4B-It
llama_model_loader: - kv 3: general.finetune str = it
llama_model_loader: - kv 4: general.basename str = Gemma-3-4B-It
llama_model_loader: - kv 5: general.quantized_by str = Unsloth
llama_model_loader: - kv 6: general.size_label str = 4B
llama_model_loader: - kv 7: general.repo_url str = https://huggingface.co/unsloth
llama_model_loader: - kv 8: gemma3.context_length u32 = 131072
llama_model_loader: - kv 9: gemma3.embedding_length u32 = 2560
llama_model_loader: - kv 10: gemma3.block_count u32 = 34
llama_model_loader: - kv 11: gemma3.feed_forward_length u32 = 10240
llama_model_loader: - kv 12: gemma3.attention.head_count u32 = 8
llama_model_loader: - kv 13: gemma3.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 14: gemma3.attention.key_length u32 = 256
llama_model_loader: - kv 15: gemma3.attention.value_length u32 = 256
llama_model_loader: - kv 16: gemma3.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 17: gemma3.attention.sliding_window u32 = 1024
llama_model_loader: - kv 18: gemma3.attention.head_count_kv u32 = 4
llama_model_loader: - kv 19: gemma3.rope.scaling.type str = linear
llama_model_loader: - kv 20: gemma3.rope.scaling.factor f32 = 8.000000
llama_model_loader: - kv 21: tokenizer.ggml.model str = llama
llama_model_loader: - kv 22: tokenizer.ggml.pre str = default
llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,262208] = ["<pad>", "<eos>", "<bos>", "<unk>", ...
llama_model_loader: - kv 24: tokenizer.ggml.scores arr[f32,262208] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 25: tokenizer.ggml.token_type arr[i32,262208] = [3, 3, 3, 3, 3, 4, 3, 3, 3, 3, 3, 3, ...
llama_model_loader: - kv 26: tokenizer.ggml.bos_token_id u32 = 2
llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 106
llama_model_loader: - kv 28: tokenizer.ggml.unknown_token_id u32 = 3
llama_model_loader: - kv 29: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 30: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 32: tokenizer.chat_template str = {{ bos_token }}\n{%- if messages[0]['r...
llama_model_loader: - kv 33: tokenizer.ggml.add_space_prefix bool = false
llama_model_loader: - kv 34: general.quantization_version u32 = 2
llama_model_loader: - kv 35: general.file_type u32 = 10
llama_model_loader: - kv 36: quantize.imatrix.file str = gemma-3-4b-it-GGUF/imatrix_unsloth.dat
llama_model_loader: - kv 37: quantize.imatrix.dataset str = unsloth_calibration_gemma-3-4b-it.txt
llama_model_loader: - kv 38: quantize.imatrix.entries_count i32 = 238
llama_model_loader: - kv 39: quantize.imatrix.chunks_count i32 = 663
llama_model_loader: - type f32: 205 tensors
llama_model_loader: - type q2_K: 96 tensors
llama_model_loader: - type q3_K: 87 tensors
llama_model_loader: - type q4_K: 5 tensors
llama_model_loader: - type q6_K: 1 tensors
llama_model_loader: - type iq2_xs: 10 tensors
llama_model_loader: - type iq3_xxs: 10 tensors
llama_model_loader: - type iq3_s: 15 tensors
llama_model_loader: - type iq2_s: 10 tensors
llama_model_loader: - type iq4_xs: 5 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q2_K - Medium
print_info: file size = 1.64 GiB (3.63 BPW)
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: ssm_d_conv = 0
print_info: ssm_d_inner = 0
print_info: ssm_d_state = 0
print_info: ssm_dt_rank = 0
print_info: ssm_dt_b_c_rms = 0
print_info: model type = 4B
print_info: model params = 3.88 B
print_info: general.name = Gemma-3-4B-It
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 = 106 '<end_of_turn>'
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 = 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 = 623.79 MiB
load_tensors: CUDA1 model buffer size = 1057.42 MiB
load_tensors: CPU_Mapped model buffer size = 525.13 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 = 1
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_unified_iswa: creating non-SWA KV cache, size = 131072 cells
llama_kv_cache_unified: CUDA0 KV buffer size = 1536.00 MiB
llama_kv_cache_unified: CUDA1 KV buffer size = 1024.00 MiB
llama_kv_cache_unified: size = 2560.00 MiB (131072 cells, 5 layers, 1 seqs), K (f16): 1280.00 MiB, V (f16): 1280.00 MiB
llama_kv_cache_unified_iswa: creating SWA KV cache, size = 1536 cells
llama_kv_cache_unified: CUDA0 KV buffer size = 90.00 MiB
llama_kv_cache_unified: CUDA1 KV buffer size = 84.00 MiB
llama_kv_cache_unified: size = 174.00 MiB ( 1536 cells, 29 layers, 1 seqs), K (f16): 87.00 MiB, V (f16): 87.00 MiB
llama_context: pipeline parallelism enabled (n_copies=4)
llama_context: CUDA0 compute buffer size = 1243.51 MiB
llama_context: CUDA1 compute buffer size = 1075.14 MiB
llama_context: CUDA_Host compute buffer size = 1041.02 MiB
llama_context: graph nodes = 1369
llama_context: graph splits = 3
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
srv init: initializing slots, n_slots = 1
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 = 131072
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = 1
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_unified_iswa: creating non-SWA KV cache, size = 131072 cells
llama_kv_cache_unified: CUDA0 KV buffer size = 1536.00 MiB
llama_kv_cache_unified: CUDA1 KV buffer size = 1024.00 MiB
llama_kv_cache_unified: size = 2560.00 MiB (131072 cells, 5 layers, 1 seqs), K (f16): 1280.00 MiB, V (f16): 1280.00 MiB
llama_kv_cache_unified_iswa: creating SWA KV cache, size = 1536 cells
llama_kv_cache_unified: CUDA0 KV buffer size = 90.00 MiB
llama_kv_cache_unified: CUDA1 KV buffer size = 84.00 MiB
llama_kv_cache_unified: size = 174.00 MiB ( 1536 cells, 29 layers, 1 seqs), K (f16): 87.00 MiB, V (f16): 87.00 MiB
llama_context: pipeline parallelism enabled (n_copies=4)
llama_context: CUDA0 compute buffer size = 1243.51 MiB
llama_context: CUDA1 compute buffer size = 1075.14 MiB
llama_context: CUDA_Host compute buffer size = 1041.02 MiB
llama_context: graph nodes = 1369
llama_context: graph splits = 3
slot init: id 0 | task -1 | new slot n_ctx_slot = 131072
main: model loaded
main: chat template, chat_template: {{ bos_token }}
{%- if messages[0]['role'] == 'system' -%}
{%- if messages[0]['content'] is string -%}
{%- set first_user_prefix = messages[0]['content'] + '
' -%}
{%- else -%}
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
' -%}
{%- endif -%}
{%- set loop_messages = messages[1:] -%}
{%- else -%}
{%- set first_user_prefix = "" -%}
{%- set loop_messages = messages -%}
{%- endif -%}
{%- for message in loop_messages -%}
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
{%- endif -%}
{%- if (message['role'] == 'assistant') -%}
{%- set role = "model" -%}
{%- else -%}
{%- set role = message['role'] -%}
{%- endif -%}
{{ '<start_of_turn>' + role + '
' + (first_user_prefix if loop.first else "") }}
{%- if message['content'] is string -%}
{{ message['content'] | trim }}
{%- elif message['content'] is iterable -%}
{%- for item in message['content'] -%}
{%- if item['type'] == 'image' -%}
{{ '<start_of_image>' }}
{%- elif item['type'] == 'text' -%}
{{ item['text'] | trim }}
{%- endif -%}
{%- endfor -%}
{%- else -%}
{{ raise_exception("Invalid content type") }}
{%- endif -%}
{{ '<end_of_turn>
' }}
{%- endfor -%}
{%- if add_generation_prompt -%}
'}}
{%- endif -%}
, example_format: '<start_of_turn>user
You are a helpful assistant
Hello<end_of_turn>
<start_of_turn>model
Hi there<end_of_turn>
<start_of_turn>user
How are you?<end_of_turn>
<start_of_turn>model
'
main: server is listening on http://127.0.0.1:8080 - starting the main loop
srv update_slots: all slots are idle
srv params_from_: Chat format: Content-only
slot launch_slot_: id 0 | task 0 | processing task
slot update_slots: id 0 | task 0 | new prompt, n_ctx_slot = 131072, n_keep = 0, n_prompt_tokens = 1891
slot update_slots: id 0 | task 0 | kv cache rm [0, end)
slot update_slots: id 0 | task 0 | prompt processing progress, n_past = 1891, n_tokens = 1891, progress = 1.000000
slot update_slots: id 0 | task 0 | prompt done, n_past = 1891, n_tokens = 1891
slot release: id 0 | task 0 | stop processing: n_past = 1947, truncated = 0
slot print_timing: id 0 | task 0 |
prompt eval time = 1422.92 ms / 1891 tokens ( 0.75 ms per token, 1328.95 tokens per second)
eval time = 2336.81 ms / 57 tokens ( 41.00 ms per token, 24.39 tokens per second)
total time = 3759.74 ms / 1948 tokens
slot print_timing: id 0 | task 0 |
draft acceptance rate = 0.52542 ( 31 accepted / 59 generated)
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
srv params_from_: Chat format: Content-only
slot launch_slot_: id 0 | task 14 | processing task
slot update_slots: id 0 | task 14 | new prompt, n_ctx_slot = 131072, n_keep = 0, n_prompt_tokens = 4283
slot update_slots: id 0 | task 14 | n_past = 7, cache_tokens.size() = 1947, seq_id = 0, pos_min = 412, n_swa = 1024
slot update_slots: id 0 | task 14 | forcing full prompt re-processing due to lack of cache data (likely due to SWA, see https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
slot update_slots: id 0 | task 14 | kv cache rm [0, end)
slot update_slots: id 0 | task 14 | prompt processing progress, n_past = 2048, n_tokens = 2048, progress = 0.478170
slot update_slots: id 0 | task 14 | kv cache rm [2048, end)
slot update_slots: id 0 | task 14 | prompt processing progress, n_past = 4096, n_tokens = 2048, progress = 0.956339
slot update_slots: id 0 | task 14 | kv cache rm [4096, end)
slot update_slots: id 0 | task 14 | prompt processing progress, n_past = 4283, n_tokens = 187, progress = 1.000000
slot update_slots: id 0 | task 14 | prompt done, n_past = 4283, n_tokens = 187
decode: failed to find KV cache slot for batch of size 3
decode: failed to find KV cache slot for batch of size 2
slot release: id 0 | task 14 | stop processing: n_past = 5495, truncated = 0
slot print_timing: id 0 | task 14 |
prompt eval time = 3225.61 ms / 4283 tokens ( 0.75 ms per token, 1327.81 tokens per second)
eval time = 39301.62 ms / 1213 tokens ( 32.40 ms per token, 30.86 tokens per second)
total time = 42527.24 ms / 5496 tokens
slot print_timing: id 0 | task 14 |
draft acceptance rate = 0.71911 ( 681 accepted / 947 generated)
srv update_slots: all slots are idle
srv log_server_r: request: POST /v1/chat/completions 127.0.0.1 200
srv params_from_: Chat format: Content-only
slot launch_slot_: id 0 | task 283 | processing task
slot update_slots: id 0 | task 283 | new prompt, n_ctx_slot = 131072, n_keep = 0, n_prompt_tokens = 3060
slot update_slots: id 0 | task 283 | n_past = 7, cache_tokens.size() = 5495, seq_id = 0, pos_min = 3959, n_swa = 1024
slot update_slots: id 0 | task 283 | forcing full prompt re-processing due to lack of cache data (likely due to SWA, see https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
slot update_slots: id 0 | task 283 | kv cache rm [0, end)
slot update_slots: id 0 | task 283 | prompt processing progress, n_past = 2048, n_tokens = 2048, progress = 0.669281
slot update_slots: id 0 | task 283 | kv cache rm [2048, end)
slot update_slots: id 0 | task 283 | prompt processing progress, n_past = 3060, n_tokens = 1012, progress = 1.000000
slot update_slots: id 0 | task 283 | prompt done, n_past = 3060, n_tokens = 1012
decode: failed to find KV cache slot for batch of size 17
get_logits_ith: invalid logits id 0, reason: batch.logits[0] != true