Eval bug: BGE-M3 Embedding model is not accessible

[cdwuchun]

Name and Version

load_backend: loaded RPC backend from D:\AI\app\llama.cpp\ggml-rpc.dll
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = AMD Radeon RX 6600M (AMD proprietary driver) | uma: 0 | fp16: 1 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none
load_backend: loaded Vulkan backend from D:\AI\app\llama.cpp\ggml-vulkan.dll
load_backend: loaded CPU backend from D:\AI\app\llama.cpp\ggml-cpu-haswell.dll
version: 5361 (cf0a43b)
built with MSVC 19.43.34808.0 for x64

Operating systems

Windows

GGML backends

Vulkan

Hardware

Ryzen 7 5800H + RX 6600M

Models

bge-m3-FP16.gguf

Problem description & steps to reproduce

Failed to add the embedding model using the llama-b5361-bin-win-cuda12.4-x64 version on a workstation with RTX 4800. The reranking model, LLM model, and VLM model can all be added. Then, testing on my laptop with a Ryzen 7 5800H and RX 6600M using llama-b5361-bin-win-vulkan-x64, the embedding model that I had previously added in Dify cannot connect.

First Bad Commit

I upgrade every day, at least it's normal on May 5th.

Relevant log output

"11.Bge-m3":
    proxy: 
    aliases:
    - Bge-m3
    # `useModelName` overrides the model name in the request
    # and sends a specific name to the upstream server
    useModelName: "Bge-m3"
    cmd: >
      llama-server
      --host 0.0.0.0
      --port ${PORT}
      --model models/gpustack/bge-m3-FP16.gguf
      --ctx-size 8192
      --batch-size 8192
      --rope-scaling yarn
      --rope-freq-scale 0.75
      --embeddings
      -ngl 99
[INFO] Request ::1 "GET /upstream HTTP/1.1" 200 740 "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36 Edg/136.0.0.0" 0s
load_backend: loaded RPC backend from D:\AI\app\llama.cpp\ggml-rpc.dll
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = AMD Radeon RX 6600M (AMD proprietary driver) | uma: 0 | fp16: 1 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none
load_backend: loaded Vulkan backend from D:\AI\app\llama.cpp\ggml-vulkan.dll
load_backend: loaded CPU backend from D:\AI\app\llama.cpp\ggml-cpu-haswell.dll
build: 5361 (cf0a43bb) with MSVC 19.43.34808.0 for x64
system info: n_threads = 8, n_threads_batch = 8, total_threads = 16

system_info: n_threads = 8 (n_threads_batch = 8) / 16 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | AARCH64_REPACK = 1 |

main: binding port with default address family
main: HTTP server is listening, hostname: 0.0.0.0, port: 8081, http threads: 15
main: loading model
srv    load_model: loading model 'models/gpustack/bge-m3-FP16.gguf'
llama_model_load_from_file_impl: using device Vulkan0 (AMD Radeon RX 6600M) - 8176 MiB free
llama_model_loader: loaded meta data with 33 key-value pairs and 389 tensors from models/gpustack/bge-m3-FP16.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              = bert
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                         general.size_label str              = 567M
llama_model_loader: - kv   3:                            general.license str              = mit
llama_model_loader: - kv   4:                               general.tags arr[str,4]       = ["sentence-transformers", "feature-ex...
llama_model_loader: - kv   5:                           bert.block_count u32              = 24
llama_model_loader: - kv   6:                        bert.context_length u32              = 8192
llama_model_loader: - kv   7:                      bert.embedding_length u32              = 1024
llama_model_loader: - kv   8:                   bert.feed_forward_length u32              = 4096
llama_model_loader: - kv   9:                  bert.attention.head_count u32              = 16
llama_model_loader: - kv  10:          bert.attention.layer_norm_epsilon f32              = 0.000010
llama_model_loader: - kv  11:                          general.file_type u32              = 1
llama_model_loader: - kv  12:                      bert.attention.causal bool             = false
llama_model_loader: - kv  13:                          bert.pooling_type u32              = 2
llama_model_loader: - kv  14:                       tokenizer.ggml.model str              = t5
llama_model_loader: - kv  15:                         tokenizer.ggml.pre str              = default
srv  log_server_r: request: GET /health 127.0.0.1 503
[INFO] <11.Bge-m3> Health check error on http://localhost:8081/health, status code: 503
llama_model_loader: - kv  16:                      tokenizer.ggml.tokens arr[str,250002]  = ["<s>", "<pad>", "</s>", "<unk>", ","...
llama_model_loader: - kv  17:                      tokenizer.ggml.scores arr[f32,250002]  = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv  18:                  tokenizer.ggml.token_type arr[i32,250002]  = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  19:            tokenizer.ggml.add_space_prefix bool             = true
llama_model_loader: - kv  20:            tokenizer.ggml.token_type_count u32              = 1
llama_model_loader: - kv  21:    tokenizer.ggml.remove_extra_whitespaces bool             = true
llama_model_loader: - kv  22:        tokenizer.ggml.precompiled_charsmap arr[u8,237539]   = [0, 180, 2, 0, 0, 132, 0, 0, 0, 0, 0,...
llama_model_loader: - kv  23:                tokenizer.ggml.bos_token_id u32              = 0
llama_model_loader: - kv  24:                tokenizer.ggml.eos_token_id u32              = 2
llama_model_loader: - kv  25:            tokenizer.ggml.unknown_token_id u32              = 3
llama_model_loader: - kv  26:          tokenizer.ggml.seperator_token_id u32              = 2
llama_model_loader: - kv  27:            tokenizer.ggml.padding_token_id u32              = 1
llama_model_loader: - kv  28:                tokenizer.ggml.cls_token_id u32              = 0
llama_model_loader: - kv  29:               tokenizer.ggml.mask_token_id u32              = 250001
llama_model_loader: - kv  30:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  31:               tokenizer.ggml.add_eos_token bool             = true
llama_model_loader: - kv  32:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  244 tensors
llama_model_loader: - type  f16:  145 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = F16
print_info: file size   = 1.07 GiB (16.25 BPW)
load: model vocab missing newline token, using special_pad_id instead
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 4
load: token to piece cache size = 2.1668 MB
print_info: arch             = bert
print_info: vocab_only       = 0
print_info: n_ctx_train      = 8192
print_info: n_embd           = 1024
print_info: n_layer          = 24
print_info: n_head           = 16
print_info: n_head_kv        = 16
print_info: n_rot            = 64
print_info: n_swa            = 0
print_info: n_swa_pattern    = 1
print_info: n_embd_head_k    = 64
print_info: n_embd_head_v    = 64
print_info: n_gqa            = 1
print_info: n_embd_k_gqa     = 1024
print_info: n_embd_v_gqa     = 1024
print_info: f_norm_eps       = 1.0e-05
print_info: f_norm_rms_eps   = 0.0e+00
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             = 4096
print_info: n_expert         = 0
print_info: n_expert_used    = 0
print_info: causal attn      = 0
print_info: pooling type     = 2
print_info: rope type        = 2
print_info: rope scaling     = linear
print_info: freq_base_train  = 10000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 8192
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       = 335M
print_info: model params     = 566.70 M
print_info: general.name     = n/a
print_info: vocab type       = UGM
print_info: n_vocab          = 250002
print_info: n_merges         = 0
print_info: BOS token        = 0 '<s>'
print_info: EOS token        = 2 '</s>'
print_info: UNK token        = 3 '<unk>'
print_info: SEP token        = 2 '</s>'
print_info: PAD token        = 1 '<pad>'
print_info: MASK token       = 250001 '[PAD250000]'
print_info: LF token         = 0 '<s>'
print_info: EOG token        = 2 '</s>'
print_info: max token length = 48
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:      Vulkan0 model buffer size =   577.22 MiB
load_tensors:   CPU_Mapped model buffer size =   520.30 MiB
.......................................................
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 8192
llama_context: n_ctx_per_seq = 8192
llama_context: n_batch       = 8192
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 0
llama_context: flash_attn    = 0
llama_context: freq_base     = 10000.0
llama_context: freq_scale    = 0.75
llama_context: Vulkan_Host  output buffer size =     0.00 MiB
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 = 8192
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
decode: cannot decode batches with this context (use llama_encode() instead)
srv          init: initializing slots, n_slots = 1
slot         init: id  0 | task -1 | new slot n_ctx_slot = 8192
main: model loaded
main: chat template, chat_template: {%- for message in messages -%}
  {{- '<|im_start|>' + message.role + '
' + message.content + '<|im_end|>
' -}}
{%- endfor -%}
{%- if add_generation_prompt -%}
  {{- '<|im_start|>assistant
' -}}
{%- endif -%}, example_format: '<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
Hello<|im_end|>
<|im_start|>assistant
Hi there<|im_end|>
<|im_start|>user
How are you?<|im_end|>
<|im_start|>assistant
'
main: server is listening on http://0.0.0.0:8081 - starting the main loop
srv  update_slots: all slots are idle
[INFO] <11.Bge-m3> Health check passed on http://localhost:8081/health

srv  log_server_r: request: POST /embeddings 172.31.137.1 200
slot launch_slot_: id  0 | task 2 | processing task
slot update_slots: id  0 | task 2 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 26
slot update_slots: id  0 | task 2 | kv cache rm [0, end)
slot update_slots: id  0 | task 2 | prompt processing progress, n_past = 26, n_tokens = 26, progress = 1.000000
slot update_slots: id  0 | task 2 | prompt done, n_past = 26, n_tokens = 26
slot      release: id  0 | task 2 | stop processing: n_past = 26, truncated = 0
srv  update_slots: all slots are idle
srv  log_server_r: request: POST /embeddings 172.31.137.1 200
slot launch_slot_: id  0 | task 4 | processing task
slot update_slots: id  0 | task 4 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 5
slot update_slots: id  0 | task 4 | kv cache rm [0, end)
slot update_slots: id  0 | task 4 | prompt processing progress, n_past = 5, n_tokens = 5, progress = 1.000000
slot update_slots: id  0 | task 4 | prompt done, n_past = 5, n_tokens = 5
slot      release: id  0 | task 4 | stop processing: n_past = 5, truncated = 0
srv  update_slots: all slots are idle
srv  log_server_r: request: POST /embeddings 172.31.137.1 200
slot launch_slot_: id  0 | task 6 | processing task
slot update_slots: id  0 | task 6 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 8
slot update_slots: id  0 | task 6 | kv cache rm [0, end)
slot update_slots: id  0 | task 6 | prompt processing progress, n_past = 8, n_tokens = 8, progress = 1.000000
slot update_slots: id  0 | task 6 | prompt done, n_past = 8, n_tokens = 8
slot      release: id  0 | task 6 | stop processing: n_past = 8, truncated = 0
srv  update_slots: all slots are idle
srv  log_server_r: request: POST /embeddings 172.31.137.1 200
slot launch_slot_: id  0 | task 8 | processing task
slot update_slots: id  0 | task 8 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 7
slot update_slots: id  0 | task 8 | kv cache rm [0, end)
slot update_slots: id  0 | task 8 | prompt processing progress, n_past = 7, n_tokens = 7, progress = 1.000000
slot update_slots: id  0 | task 8 | prompt done, n_past = 7, n_tokens = 7
slot      release: id  0 | task 8 | stop processing: n_past = 7, truncated = 0
slot launch_slot_: id  0 | task 10 | processing task
slot update_slots: id  0 | task 10 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 9
slot update_slots: id  0 | task 10 | kv cache rm [0, end)
slot update_slots: id  0 | task 10 | prompt processing progress, n_past = 9, n_tokens = 9, progress = 1.000000
slot update_slots: id  0 | task 10 | prompt done, n_past = 9, n_tokens = 9
srv  log_server_r: request: POST /embeddings 172.31.137.1 200
slot      release: id  0 | task 10 | stop processing: n_past = 9, truncated = 0
srv  update_slots: all slots are idle
srv  log_server_r: request: POST /embeddings 172.31.137.1 200
slot launch_slot_: id  0 | task 12 | processing task
slot update_slots: id  0 | task 12 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 9
slot update_slots: id  0 | task 12 | kv cache rm [0, end)
slot update_slots: id  0 | task 12 | prompt processing progress, n_past = 9, n_tokens = 9, progress = 1.000000
slot update_slots: id  0 | task 12 | prompt done, n_past = 9, n_tokens = 9
slot      release: id  0 | task 12 | stop processing: n_past = 9, truncated = 0
srv  update_slots: all slots are idle
srv  log_server_r: request: POST /embeddings 172.31.137.1 200
slot launch_slot_: id  0 | task 14 | processing task
slot update_slots: id  0 | task 14 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 8
slot update_slots: id  0 | task 14 | kv cache rm [0, end)
slot update_slots: id  0 | task 14 | prompt processing progress, n_past = 8, n_tokens = 8, progress = 1.000000
slot update_slots: id  0 | task 14 | prompt done, n_past = 8, n_tokens = 8
slot      release: id  0 | task 14 | stop processing: n_past = 8, truncated = 0
slot launch_slot_: id  0 | task 16 | processing task
slot update_slots: id  0 | task 16 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 7
slot update_slots: id  0 | task 16 | kv cache rm [0, end)
slot update_slots: id  0 | task 16 | prompt processing progress, n_past = 7, n_tokens = 7, progress = 1.000000
slot update_slots: id  0 | task 16 | prompt done, n_past = 7, n_tokens = 7
srv  log_server_r: request: POST /embeddings 172.31.137.1 200
slot      release: id  0 | task 16 | stop processing: n_past = 7, truncated = 0
srv  update_slots: all slots are idle
srv  log_server_r: request: POST /embeddings 172.31.137.1 200
slot launch_slot_: id  0 | task 18 | processing task
slot update_slots: id  0 | task 18 | new prompt, n_ctx_slot = 8192, n_keep = 0, n_prompt_tokens = 9
slot update_slots: id  0 | task 18 | kv cache rm [0, end)
slot update_slots: id  0 | task 18 | prompt processing progress, n_past = 9, n_tokens = 9, progress = 1.000000
slot update_slots: id  0 | task 18 | prompt done, n_past = 9, n_tokens = 9
slot      release: id  0 | task 18 | stop processing: n_past = 9, truncated = 0
srv  update_slots: all slots are idle
srv  log_server_r: request: POST /embeddings 172.31.137.1 200

[cdwuchun]

The feedback from dify is:Credentials validation failed: invalid response