github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4803] Run chat api with Llama3 8B Model converted by llama.cpp had infinity response time #3030

New Issue
Closed
opened 2026-04-12 13:26:36 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 13:26:36 -05:00
Owner
Copy Link

Originally created by @cuongnguyengit on GitHub (Jun 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4803

What is the issue?

Hi team,

I used your guide (https://github.com/ollama/ollama/blob/main/docs/import.md) to convert https://huggingface.co/hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode to gguf file.

All of conversions were ok but when I run with ollama I get the following error:

llama_new_context_with_model: graph splits = 5
{"function":"initialize","level":"INFO","line":448,"msg":"initializing slots","n_slots":1,"tid":"139847421562880","timestamp":1717470350}
{"function":"initialize","level":"INFO","line":457,"msg":"new slot","n_ctx_slot":2048,"slot_id":0,"tid":"139847421562880","timestamp":1717470350}
{"function":"main","level":"INFO","line":3064,"msg":"model loaded","tid":"139847421562880","timestamp":1717470350}
{"function":"validate_model_chat_template","level":"ERR","line":437,"msg":"The chat template comes with this model is not yet supported, falling back to chatml. This may cause the model to output suboptimal responses","tid":"139847421562880","timestamp":1717470350}
{"function":"main","hostname":"127.0.0.1","level":"INFO","line":3267,"msg":"HTTP server listening","n_threads_http":"71","port":"24108","tid":"139847421562880","timestamp":1717470350}
{"function":"update_slots","level":"INFO","line":1578,"msg":"all slots are idle and system prompt is empty, clear the KV cache","tid":"139847421562880","timestamp":1717470350}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":0,"tid":"139847421562880","timestamp":1717470350}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1,"tid":"139847421562880","timestamp":1717470350}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6688,"status":200,"tid":"139843732500480","timestamp":1717470350}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":2,"tid":"139847421562880","timestamp":1717470350}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6690,"status":200,"tid":"139843724107776","timestamp":1717470350}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":3,"tid":"139847421562880","timestamp":1717470350}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6692,"status":200,"tid":"139843707322368","timestamp":1717470350}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":4,"tid":"139847421562880","timestamp":1717470350}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6694,"status":200,"tid":"139843715715072","timestamp":1717470350}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":5,"tid":"139847421562880","timestamp":1717470350}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6696,"status":200,"tid":"139843698929664","timestamp":1717470350}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6698,"status":200,"tid":"139843690536960","timestamp":1717470350}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":6,"tid":"139847421562880","timestamp":1717470350}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6810,"status":200,"tid":"139843598282752","timestamp":1717470350}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":7,"tid":"139847421562880","timestamp":1717470350}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6810,"status":200,"tid":"139843598282752","timestamp":1717470350}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":8,"tid":"139847421562880","timestamp":1717470350}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6802,"status":200,"tid":"139843589890048","timestamp":1717470350}
{"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/tokenize","remote_addr":"127.0.0.1","remote_port":6810,"status":200,"tid":"139843598282752","timestamp":1717470350}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":9,"tid":"139847421562880","timestamp":1717470350}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6776,"status":200,"tid":"139843581497344","timestamp":1717470350}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":10,"tid":"139847421562880","timestamp":1717470350}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6810,"status":200,"tid":"139843598282752","timestamp":1717470350}
{"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":11,"tid":"139847421562880","timestamp":1717470350}
{"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":0,"n_past_se":0,"n_prompt_tokens_processed":188,"slot_id":0,"task_id":11,"tid":"139847421562880","timestamp":1717470350}
{"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":0,"slot_id":0,"task_id":11,"tid":"139847421562880","timestamp":1717470350}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":13,"tid":"139847421562880","timestamp":1717470350}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6804,"status":200,"tid":"139843573104640","timestamp":1717470350}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":34,"tid":"139847421562880","timestamp":1717470351}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6752,"status":200,"tid":"139843564711936","timestamp":1717470351}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":44,"tid":"139847421562880","timestamp":1717470351}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6788,"status":200,"tid":"139843556319232","timestamp":1717470351}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":47,"tid":"139847421562880","timestamp":1717470351}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6756,"status":200,"tid":"139843547926528","timestamp":1717470351}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":52,"tid":"139847421562880","timestamp":1717470351}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6790,"status":200,"tid":"139843539533824","timestamp":1717470351}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":72,"tid":"139847421562880","timestamp":1717470352}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6764,"status":200,"tid":"139843531141120","timestamp":1717470352}
{"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":97,"tid":"139847421562880","timestamp":1717470353}
{"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6772,"status":200,"tid":"139843682144256","timestamp":1717470353}

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.1.32

Originally created by @cuongnguyengit on GitHub (Jun 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4803 ### What is the issue? Hi team, I used your guide (https://github.com/ollama/ollama/blob/main/docs/import.md) to convert https://huggingface.co/hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode to gguf file. All of conversions were ok but when I run with ollama I get the following error: llama_new_context_with_model: graph splits = 5 {"function":"initialize","level":"INFO","line":448,"msg":"initializing slots","n_slots":1,"tid":"139847421562880","timestamp":1717470350} {"function":"initialize","level":"INFO","line":457,"msg":"new slot","n_ctx_slot":2048,"slot_id":0,"tid":"139847421562880","timestamp":1717470350} {"function":"main","level":"INFO","line":3064,"msg":"model loaded","tid":"139847421562880","timestamp":1717470350} {"function":"validate_model_chat_template","level":"ERR","line":437,"msg":"The chat template comes with this model is not yet supported, falling back to chatml. This may cause the model to output suboptimal responses","tid":"139847421562880","timestamp":1717470350} {"function":"main","hostname":"127.0.0.1","level":"INFO","line":3267,"msg":"HTTP server listening","n_threads_http":"71","port":"24108","tid":"139847421562880","timestamp":1717470350} {"function":"update_slots","level":"INFO","line":1578,"msg":"all slots are idle and system prompt is empty, clear the KV cache","tid":"139847421562880","timestamp":1717470350} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":0,"tid":"139847421562880","timestamp":1717470350} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":1,"tid":"139847421562880","timestamp":1717470350} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6688,"status":200,"tid":"139843732500480","timestamp":1717470350} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":2,"tid":"139847421562880","timestamp":1717470350} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6690,"status":200,"tid":"139843724107776","timestamp":1717470350} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":3,"tid":"139847421562880","timestamp":1717470350} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6692,"status":200,"tid":"139843707322368","timestamp":1717470350} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":4,"tid":"139847421562880","timestamp":1717470350} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6694,"status":200,"tid":"139843715715072","timestamp":1717470350} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":5,"tid":"139847421562880","timestamp":1717470350} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6696,"status":200,"tid":"139843698929664","timestamp":1717470350} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6698,"status":200,"tid":"139843690536960","timestamp":1717470350} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":6,"tid":"139847421562880","timestamp":1717470350} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6810,"status":200,"tid":"139843598282752","timestamp":1717470350} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":7,"tid":"139847421562880","timestamp":1717470350} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6810,"status":200,"tid":"139843598282752","timestamp":1717470350} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":8,"tid":"139847421562880","timestamp":1717470350} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6802,"status":200,"tid":"139843589890048","timestamp":1717470350} {"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/tokenize","remote_addr":"127.0.0.1","remote_port":6810,"status":200,"tid":"139843598282752","timestamp":1717470350} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":9,"tid":"139847421562880","timestamp":1717470350} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6776,"status":200,"tid":"139843581497344","timestamp":1717470350} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":10,"tid":"139847421562880","timestamp":1717470350} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6810,"status":200,"tid":"139843598282752","timestamp":1717470350} {"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing task","slot_id":0,"task_id":11,"tid":"139847421562880","timestamp":1717470350} {"function":"update_slots","ga_i":0,"level":"INFO","line":1809,"msg":"slot progression","n_past":0,"n_past_se":0,"n_prompt_tokens_processed":188,"slot_id":0,"task_id":11,"tid":"139847421562880","timestamp":1717470350} {"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":0,"slot_id":0,"task_id":11,"tid":"139847421562880","timestamp":1717470350} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":13,"tid":"139847421562880","timestamp":1717470350} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6804,"status":200,"tid":"139843573104640","timestamp":1717470350} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":34,"tid":"139847421562880","timestamp":1717470351} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6752,"status":200,"tid":"139843564711936","timestamp":1717470351} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":44,"tid":"139847421562880","timestamp":1717470351} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6788,"status":200,"tid":"139843556319232","timestamp":1717470351} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":47,"tid":"139847421562880","timestamp":1717470351} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6756,"status":200,"tid":"139843547926528","timestamp":1717470351} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":52,"tid":"139847421562880","timestamp":1717470351} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6790,"status":200,"tid":"139843539533824","timestamp":1717470351} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":72,"tid":"139847421562880","timestamp":1717470352} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6764,"status":200,"tid":"139843531141120","timestamp":1717470352} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":0,"n_processing_slots":1,"task_id":97,"tid":"139847421562880","timestamp":1717470353} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":6772,"status":200,"tid":"139843682144256","timestamp":1717470353} ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.32
GiteaMirror added the bug label 2026-04-12 13:26:36 -05:00
GiteaMirror commented 2026-04-12 13:26:39 -05:00
Author
Owner
Copy Link

@cuongnguyengit commented on GitHub (Jun 4, 2024):

My template: TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>

{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>

{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>

{{ .Response }}<|eot_id|>"""
PARAMETER num_keep 24
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop ""<|eot_id|>""

<!-- gh-comment-id:2146520662 --> @cuongnguyengit commented on GitHub (Jun 4, 2024): My template: TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> {{ .Response }}<|eot_id|>""" PARAMETER num_keep 24 PARAMETER stop "<|start_header_id|>" PARAMETER stop "<|end_header_id|>" PARAMETER stop "\"<|eot_id|>\""
GiteaMirror commented 2026-04-12 13:26:42 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jun 5, 2024):

@cuongnguyengit can you upgrade to the latest version of ollama? There were numerous fixes that had to be done to llama3 due to its vocabulary and how it uses stop tokens.

I'm going to go ahead and close the issue, but we can reopen this if it's still a problem on newer versions.

<!-- gh-comment-id:2150934129 --> @pdevine commented on GitHub (Jun 5, 2024): @cuongnguyengit can you upgrade to the latest version of ollama? There were numerous fixes that had to be done to llama3 due to its vocabulary and how it uses stop tokens. I'm going to go ahead and close the issue, but we can reopen this if it's still a problem on newer versions.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#3030
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?