Name and Version
llama-server --version
version: 6962 (230d116)
built with clang version 19.1.5 for x86_64-pc-windows-msvc
Note:
I have a Linux machine with
llama-server --version
version: 6377 (5421f63)
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
The same code runs there absolutely fine, so i think this is a regression.
Operating systems
Windows
Which llama.cpp modules do you know to be affected?
llama-server
Command line
llama-server -hf ggml-org/gemma-3-4b-it-qat-GGUF -c 131072 -fa on --port 8080
Problem description & steps to reproduce
Start server with
llama-server -hf ggml-org/gemma-3-4b-it-qat-GGUF -c 131072 -fa on --port 8080
When sending a prompt via Python:
data = {
"messages": [{"role":"user", "content": prompt}],
"stream": True,
"json_schema": json_schema,
"cache_prompt": True,
"reasoning_format": "none",
"samplers":"edkypmxt",
"temperature": 0.8,
"dynatemp_range": 0,
"dynatemp_exponent": 1,
"top_k": 40,
"top_p": 0.95,
"min_p": 0.05,
"typical_p": 1,
"xtc_probability": 0,
"xtc_threshold": 0.1,
"repeat_last_n": 64,
"repeat_penalty": 1,
"presence_penalty": 0,
"frequency_penalty": 0,
"dry_multiplier": 0,
"dry_base": 1.75,
"dry_allowed_length": 2,
"dry_penalty_last_n": -1,
"max_tokens": -1,
"timings_per_token": False
}
response = requests.post(url=url, headers=headers, json=data, stream=True)
the server crashes with:
slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = -1
slot launch_slot_: id 0 | task 892 | processing task
slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 158531419
slot launch_slot_: id 3 | task 893 | processing task
slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 220460900
slot launch_slot_: id 2 | task 894 | processing task
slot update_slots: id 0 | task 892 | new prompt, n_ctx_slot = 131072, n_keep = 0, task.n_tokens = 1094
slot update_slots: id 0 | task 892 | n_tokens = 0, memory_seq_rm [0, end)
slot update_slots: id 0 | task 892 | prompt processing progress, n_tokens = 1030, batch.n_tokens = 1030, progress = 0.941499
slot update_slots: id 1 | task 890 | n_tokens = 686, memory_seq_rm [686, end)
slot update_slots: id 1 | task 890 | prompt processing progress, n_tokens = 750, batch.n_tokens = 1094, progress = 1.000000
slot update_slots: id 1 | task 890 | prompt done, n_tokens = 750, batch.n_tokens = 1094
slot update_slots: id 1 | task 890 | created context checkpoint 1 of 8 (pos_min = 0, pos_max = 685, size = 77.719 MiB)
D:/a/llama.cpp/llama.cpp/tools/server/server.cpp:3887: GGML_ASSERT(!slot.prompt.tokens.has_mtmd) failed
slot update_slots: id 2 | task 894 | new prompt, n_ctx_slot = 131072, n_keep = 0, task.n_tokens = 775
First Bad Commit
No response
Relevant log output
load_backend: loaded RPC backend from C:\Users\***\AppData\Local\Microsoft\WinGet\Packages\ggml.llamacpp_Microsoft.Winget.Source_8wekyb3d8bbwe\ggml-rpc.dll
ggml_vulkan: Found 2 Vulkan devices:
ggml_vulkan: 0 = NVIDIA RTX 2000 Ada Generation Laptop GPU (NVIDIA) | uma: 0 | fp16: 1 | bf16: 1 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2
ggml_vulkan: 1 = Intel(R) Arc(TM) Graphics (Intel Corporation) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none
load_backend: loaded Vulkan backend from C:\Users\***\AppData\Local\Microsoft\WinGet\Packages\ggml.llamacpp_Microsoft.Winget.Source_8wekyb3d8bbwe\ggml-vulkan.dll
load_backend: loaded CPU backend from C:\Users\***\AppData\Local\Microsoft\WinGet\Packages\ggml.llamacpp_Microsoft.Winget.Source_8wekyb3d8bbwe\ggml-cpu-alderlake.dll
* Host huggingface.co:443 was resolved.
* IPv6: (none)
* IPv4: 52.222.136.92, 52.222.136.89, 52.222.136.117, 52.222.136.38
* Trying 52.222.136.92:443...
* Connected to huggingface.co (52.222.136.92) port 443
* ALPN: curl offers h2,http/1.1
* successfully imported Windows ROOT store
* successfully imported Windows CA store
* SSL connection using TLSv1.3 / TLS_AES_128_GCM_SHA256 / [blank] / UNDEF
* ALPN: server accepted h2
* Server certificate:
* subject: CN=huggingface.co
* start date: Apr 13 00:00:00 2025 GMT
* expire date: May 12 23:59:59 2026 GMT
* subjectAltName: host "huggingface.co" matched cert's "huggingface.co"
* issuer: C=US; O=Amazon; CN=Amazon RSA 2048 M02
* SSL certificate verify ok.
* Certificate level 0: Public key type ? (2048/112 Bits/secBits), signed using sha256WithRSAEncryption
* Certificate level 1: Public key type ? (2048/112 Bits/secBits), signed using sha256WithRSAEncryption
* Certificate level 2: Public key type ? (2048/112 Bits/secBits), signed using sha256WithRSAEncryption
* using HTTP/2
* [HTTP/2] [1] OPENED stream for https://huggingface.co/v2/ggml-org/gemma-3-4b-it-qat-GGUF/manifests/latest
* [HTTP/2] [1] [:method: GET]
* [HTTP/2] [1] [:scheme: https]
* [HTTP/2] [1] [:authority: huggingface.co]
* [HTTP/2] [1] [:path: /v2/ggml-org/gemma-3-4b-it-qat-GGUF/manifests/latest]
* [HTTP/2] [1] [user-agent: llama-cpp]
* [HTTP/2] [1] [accept: application/json]
> GET /v2/ggml-org/gemma-3-4b-it-qat-GGUF/manifests/latest HTTP/2
Host: huggingface.co
User-Agent: llama-cpp
Accept: application/json
< HTTP/2 200
< content-type: application/json; charset=utf-8
< content-length: 1412
< date: Fri, 07 Nov 2025 10:23:18 GMT
< etag: W/"584-7g0TV0F+oWpH0AQQku/7TCKznZs"
< x-powered-by: huggingface-moon
< x-request-id: Root=1-690dc896-586a3f232013631b0f6534f2
< ratelimit: "pages";r=97;t=10
< ratelimit-policy: "fixed window";"pages";q=100;w=300
< cross-origin-opener-policy: same-origin
< referrer-policy: strict-origin-when-cross-origin
< access-control-max-age: 86400
< access-control-allow-origin: https://huggingface.co
< vary: Origin
< access-control-expose-headers: X-Repo-Commit,X-Request-Id,X-Error-Code,X-Error-Message,X-Total-Count,ETag,Link,Accept-Ranges,Content-Range,X-Linked-Size,X-Linked-ETag,X-Xet-Hash
< x-cache: Miss from cloudfront
< via: 1.1 79006a1b1266ae3c597864512702ebf8.cloudfront.net (CloudFront)
< x-amz-cf-pop: FRA50-P2
< x-amz-cf-id: oT8gGCnQkGFI0gBKRUVfH-4pusm40PD9Og0Uu1oGu_HJeIi-P2uLYQ==
<
* Connection #0 to host huggingface.co left intact
write_file: unable to rename file: C:\Users\***\AppData\Local\llama.cpp\manifest=ggml-org_gemma-3-4b-it-qat-GGUF=latest.json.tmp to C:\Users\***\AppData\Local\llama.cpp\manifest=ggml-org_gemma-3-4b-it-qat-GGUF=latest.json
common_download_file_single_online: using cached file: C:\Users\***\AppData\Local\llama.cpp\ggml-org_gemma-3-4b-it-qat-GGUF_gemma-3-4b-it-qat-Q4_0.gguf
common_download_file_single_online: using cached file: C:\Users\***\AppData\Local\llama.cpp\ggml-org_gemma-3-4b-it-qat-GGUF_mmproj-model-f16-4B.gguf
main: setting n_parallel = 4 and kv_unified = true (add -kvu to disable this)
build: 6962 (230d1169e) with clang version 19.1.5 for x86_64-pc-windows-msvc
system info: n_threads = 16, n_threads_batch = 16, total_threads = 22
system_info: n_threads = 16 (n_threads_batch = 16) / 22 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 |
main: binding port with default address family
main: HTTP server is listening, hostname: 127.0.0.1, port: 8080, http threads: 21
main: loading model
srv load_model: loading model 'C:\Users\***\AppData\Local\llama.cpp\ggml-org_gemma-3-4b-it-qat-GGUF_gemma-3-4b-it-qat-Q4_0.gguf'
llama_model_load_from_file_impl: using device Vulkan0 (NVIDIA RTX 2000 Ada Generation Laptop GPU) (0000:01:00.0) - 7189 MiB free
llama_model_loader: loaded meta data with 41 key-value pairs and 444 tensors from C:\Users\***\AppData\Local\llama.cpp\ggml-org_gemma-3-4b-it-qat-GGUF_gemma-3-4b-it-qat-Q4_0.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 Qat Q4_0 Unquantized
llama_model_loader: - kv 3: general.finetune str = it-qat-unquantized
llama_model_loader: - kv 4: general.basename str = gemma-3
llama_model_loader: - kv 5: general.size_label str = 4B
llama_model_loader: - kv 6: general.license str = gemma
llama_model_loader: - kv 7: general.base_model.count u32 = 1
llama_model_loader: - kv 8: general.base_model.0.name str = Gemma 3 4b It
llama_model_loader: - kv 9: general.base_model.0.organization str = Google
llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/google/gemma-3...
llama_model_loader: - kv 11: general.tags arr[str,4] = ["gemma3", "gemma", "google", "image-...
llama_model_loader: - kv 12: gemma3.context_length u32 = 131072
llama_model_loader: - kv 13: gemma3.embedding_length u32 = 2560
llama_model_loader: - kv 14: gemma3.block_count u32 = 34
llama_model_loader: - kv 15: gemma3.feed_forward_length u32 = 10240
llama_model_loader: - kv 16: gemma3.attention.head_count u32 = 8
llama_model_loader: - kv 17: gemma3.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 18: gemma3.attention.key_length u32 = 256
llama_model_loader: - kv 19: gemma3.attention.value_length u32 = 256
llama_model_loader: - kv 20: gemma3.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 21: gemma3.attention.sliding_window u32 = 1024
llama_model_loader: - kv 22: gemma3.attention.head_count_kv u32 = 4
llama_model_loader: - kv 23: gemma3.rope.scaling.type str = linear
llama_model_loader: - kv 24: gemma3.rope.scaling.factor f32 = 8.000000
llama_model_loader: - kv 25: tokenizer.ggml.model str = llama
llama_model_loader: - kv 26: tokenizer.ggml.pre str = default
llama_model_loader: - kv 27: tokenizer.ggml.tokens arr[str,262208] = ["<pad>", "<eos>", "<bos>", "<unk>", ...
llama_model_loader: - kv 28: tokenizer.ggml.scores arr[f32,262208] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 29: tokenizer.ggml.token_type arr[i32,262208] = [3, 3, 3, 3, 3, 4, 3, 3, 3, 3, 3, 3, ...
llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 2
llama_model_loader: - kv 31: tokenizer.ggml.eos_token_id u32 = 1
llama_model_loader: - kv 32: tokenizer.ggml.unknown_token_id u32 = 3
llama_model_loader: - kv 33: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 34: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 35: tokenizer.ggml.add_sep_token bool = false
llama_model_loader: - kv 36: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 37: tokenizer.chat_template str = {{ bos_token }}\n{%- if messages[0]['r...
llama_model_loader: - kv 38: tokenizer.ggml.add_space_prefix bool = false
llama_model_loader: - kv 39: general.quantization_version u32 = 2
llama_model_loader: - kv 40: general.file_type u32 = 2
llama_model_loader: - type f32: 205 tensors
llama_model_loader: - type q4_0: 238 tensors
llama_model_loader: - type q8_0: 1 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_0
print_info: file size = 2.35 GiB (5.19 BPW)
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: printing all EOG tokens:
load: - 1 ('<eos>')
load: - 106 ('<end_of_turn>')
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: n_expert_groups = 0
print_info: n_group_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: model type = 4B
print_info: model params = 3.88 B
print_info: general.name = Gemma 3 4b It Qat Q4_0 Unquantized
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 = 1 '<eos>'
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 = 1 '<eos>'
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: CPU_Mapped model buffer size = 680.17 MiB
load_tensors: Vulkan0 model buffer size = 2402.82 MiB
..........................................................
llama_context: constructing llama_context
llama_context: n_seq_max = 4
llama_context: n_ctx = 131072
llama_context: n_ctx_seq = 131072
llama_context: n_batch = 2048
llama_context: n_ubatch = 512
llama_context: causal_attn = 1
llama_context: flash_attn = enabled
llama_context: kv_unified = true
llama_context: freq_base = 1000000.0
llama_context: freq_scale = 0.125
llama_context: Vulkan_Host output buffer size = 4.00 MiB
llama_kv_cache_iswa: creating non-SWA KV cache, size = 131072 cells
llama_kv_cache: Vulkan0 KV buffer size = 2560.00 MiB
llama_kv_cache: size = 2560.00 MiB (131072 cells, 5 layers, 4/1 seqs), K (f16): 1280.00 MiB, V (f16): 1280.00 MiB
llama_kv_cache_iswa: creating SWA KV cache, size = 4608 cells
llama_kv_cache: Vulkan0 KV buffer size = 522.00 MiB
llama_kv_cache: size = 522.00 MiB ( 4608 cells, 29 layers, 4/1 seqs), K (f16): 261.00 MiB, V (f16): 261.00 MiB
llama_context: Vulkan0 compute buffer size = 517.12 MiB
llama_context: Vulkan_Host compute buffer size = 270.02 MiB
llama_context: graph nodes = 1369
llama_context: graph splits = 2
common_init_from_params: added <eos> logit bias = -inf
common_init_from_params: added <end_of_turn> logit bias = -inf
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)
clip_model_loader: model name: Gemma 3 4b It Qat Q4_0 Unquantized
clip_model_loader: description:
clip_model_loader: GGUF version: 3
clip_model_loader: alignment: 32
clip_model_loader: n_tensors: 439
clip_model_loader: n_kv: 27
clip_model_loader: has vision encoder
clip_ctx: CLIP using Vulkan0 backend
load_hparams: projector: gemma3
load_hparams: n_embd: 1152
load_hparams: n_head: 16
load_hparams: n_ff: 4304
load_hparams: n_layer: 27
load_hparams: ffn_op: gelu
load_hparams: projection_dim: 2560
--- vision hparams ---
load_hparams: image_size: 896
load_hparams: patch_size: 14
load_hparams: has_llava_proj: 0
load_hparams: minicpmv_version: 0
load_hparams: n_merge: 4
load_hparams: n_wa_pattern: 0
load_hparams: model size: 811.79 MiB
load_hparams: metadata size: 0.15 MiB
alloc_compute_meta: warmup with image size = 896 x 896
alloc_compute_meta: Vulkan0 compute buffer size = 121.25 MiB
alloc_compute_meta: CPU compute buffer size = 9.19 MiB
alloc_compute_meta: graph splits = 1, nodes = 863
warmup: flash attention is enabled
srv load_model: loaded multimodal model, 'C:\Users\***\AppData\Local\llama.cpp\ggml-org_gemma-3-4b-it-qat-GGUF_mmproj-model-f16-4B.gguf'
srv init: initializing slots, n_slots = 4
slot init: id 0 | task -1 | new slot, n_ctx = 131072
slot init: id 1 | task -1 | new slot, n_ctx = 131072
slot init: id 2 | task -1 | new slot, n_ctx = 131072
slot init: id 3 | task -1 | new slot, n_ctx = 131072
srv init: prompt cache is enabled, size limit: 8192 MiB
srv init: use `--cache-ram 0` to disable the prompt cache
srv init: for more info see https://github.com/ggml-org/llama.cpp/pull/16391
srv init: thinking = 0
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 -%}
{{'<start_of_turn>model
'}}
{%- 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 log_server_r: request: POST /v1/chat/completions 127.0.0.1 400
srv params_from_: Chat format: Content-only
slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = -1
slot launch_slot_: id 3 | task 0 | processing task
slot update_slots: id 3 | task 0 | new prompt, n_ctx_slot = 131072, n_keep = 0, task.n_tokens = 493
slot update_slots: id 3 | task 0 | n_tokens = 0, memory_seq_rm [0, end)
slot update_slots: id 3 | task 0 | prompt processing progress, n_tokens = 429, batch.n_tokens = 429, progress = 0.870183
slot update_slots: id 3 | task 0 | n_tokens = 429, memory_seq_rm [429, end)
slot update_slots: id 3 | task 0 | prompt processing progress, n_tokens = 493, batch.n_tokens = 64, progress = 1.000000
slot update_slots: id 3 | task 0 | prompt done, n_tokens = 493, batch.n_tokens = 64
slot update_slots: id 3 | task 0 | created context checkpoint 1 of 8 (pos_min = 0, pos_max = 428, size = 48.603 MiB)
slot print_timing: id 3 | task 0 |
prompt eval time = 1290.57 ms / 493 tokens ( 2.62 ms per token, 382.00 tokens per second)
eval time = 7245.86 ms / 111 tokens ( 65.28 ms per token, 15.32 tokens per second)
total time = 8536.43 ms / 604 tokens
slot release: id 3 | task 0 | stop processing: n_tokens = 603, truncated = 0
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 get_availabl: id 2 | task -1 | selected slot by LRU, t_last = -1
slot launch_slot_: id 2 | task 113 | processing task
slot update_slots: id 2 | task 113 | new prompt, n_ctx_slot = 131072, n_keep = 0, task.n_tokens = 3399
slot update_slots: id 2 | task 113 | n_tokens = 0, memory_seq_rm [0, end)
slot update_slots: id 2 | task 113 | prompt processing progress, n_tokens = 2048, batch.n_tokens = 2048, progress = 0.602530
slot update_slots: id 2 | task 113 | n_tokens = 2048, memory_seq_rm [2048, end)
slot update_slots: id 2 | task 113 | prompt processing progress, n_tokens = 3335, batch.n_tokens = 1287, progress = 0.981171
slot update_slots: id 2 | task 113 | n_tokens = 3335, memory_seq_rm [3335, end)
slot update_slots: id 2 | task 113 | prompt processing progress, n_tokens = 3399, batch.n_tokens = 64, progress = 1.000000
slot update_slots: id 2 | task 113 | prompt done, n_tokens = 3399, batch.n_tokens = 64
slot update_slots: id 2 | task 113 | created context checkpoint 1 of 8 (pos_min = 0, pos_max = 3334, size = 377.832 MiB)
slot print_timing: id 2 | task 113 |
prompt eval time = 6834.06 ms / 3399 tokens ( 2.01 ms per token, 497.36 tokens per second)
eval time = 53037.31 ms / 774 tokens ( 68.52 ms per token, 14.59 tokens per second)
total time = 59871.37 ms / 4173 tokens
slot release: id 2 | task 113 | stop processing: n_tokens = 4172, truncated = 0
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 get_availabl: id 1 | task -1 | selected slot by LRU, t_last = -1
slot launch_slot_: id 1 | task 890 | processing task
slot update_slots: id 1 | task 890 | new prompt, n_ctx_slot = 131072, n_keep = 0, task.n_tokens = 750
slot update_slots: id 1 | task 890 | n_tokens = 0, memory_seq_rm [0, end)
srv params_from_: Chat format: Content-only
slot update_slots: id 1 | task 890 | prompt processing progress, n_tokens = 686, batch.n_tokens = 686, progress = 0.914667
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
srv params_from_: Chat format: Content-only
slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = -1
slot launch_slot_: id 0 | task 892 | processing task
slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 158531419
slot launch_slot_: id 3 | task 893 | processing task
slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 220460900
slot launch_slot_: id 2 | task 894 | processing task
slot update_slots: id 0 | task 892 | new prompt, n_ctx_slot = 131072, n_keep = 0, task.n_tokens = 1094
slot update_slots: id 0 | task 892 | n_tokens = 0, memory_seq_rm [0, end)
slot update_slots: id 0 | task 892 | prompt processing progress, n_tokens = 1030, batch.n_tokens = 1030, progress = 0.941499
slot update_slots: id 1 | task 890 | n_tokens = 686, memory_seq_rm [686, end)
slot update_slots: id 1 | task 890 | prompt processing progress, n_tokens = 750, batch.n_tokens = 1094, progress = 1.000000
slot update_slots: id 1 | task 890 | prompt done, n_tokens = 750, batch.n_tokens = 1094
slot update_slots: id 1 | task 890 | created context checkpoint 1 of 8 (pos_min = 0, pos_max = 685, size = 77.719 MiB)
D:/a/llama.cpp/llama.cpp/tools/server/server.cpp:3887: GGML_ASSERT(!slot.prompt.tokens.has_mtmd) failed
slot update_slots: id 2 | task 894 | new prompt, n_ctx_slot = 131072, n_keep = 0, task.n_tokens = 775
Name and Version
llama-server --version
version: 6962 (230d116)
built with clang version 19.1.5 for x86_64-pc-windows-msvc
Note:
I have a Linux machine with
llama-server --version
version: 6377 (5421f63)
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
The same code runs there absolutely fine, so i think this is a regression.
Operating systems
Windows
Which llama.cpp modules do you know to be affected?
llama-server
Command line
Problem description & steps to reproduce
Start server with
llama-server -hf ggml-org/gemma-3-4b-it-qat-GGUF -c 131072 -fa on --port 8080
When sending a prompt via Python:
the server crashes with:
slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = -1
slot launch_slot_: id 0 | task 892 | processing task
slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 158531419
slot launch_slot_: id 3 | task 893 | processing task
slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 220460900
slot launch_slot_: id 2 | task 894 | processing task
slot update_slots: id 0 | task 892 | new prompt, n_ctx_slot = 131072, n_keep = 0, task.n_tokens = 1094
slot update_slots: id 0 | task 892 | n_tokens = 0, memory_seq_rm [0, end)
slot update_slots: id 0 | task 892 | prompt processing progress, n_tokens = 1030, batch.n_tokens = 1030, progress = 0.941499
slot update_slots: id 1 | task 890 | n_tokens = 686, memory_seq_rm [686, end)
slot update_slots: id 1 | task 890 | prompt processing progress, n_tokens = 750, batch.n_tokens = 1094, progress = 1.000000
slot update_slots: id 1 | task 890 | prompt done, n_tokens = 750, batch.n_tokens = 1094
slot update_slots: id 1 | task 890 | created context checkpoint 1 of 8 (pos_min = 0, pos_max = 685, size = 77.719 MiB)
D:/a/llama.cpp/llama.cpp/tools/server/server.cpp:3887: GGML_ASSERT(!slot.prompt.tokens.has_mtmd) failed
slot update_slots: id 2 | task 894 | new prompt, n_ctx_slot = 131072, n_keep = 0, task.n_tokens = 775
First Bad Commit
No response
Relevant log output