Skip to content

Can't start Qwen_Qwen3.6-27B #5

Description

@art-den

master git branch

llama.cpp output:

D:\cpp\llama.cpp\cubetitled-ui\llama.cpp\ggml\src\ggml-backend-meta.cpp:625: shape mismatch for VIEW 

I use these commands to start:

set LL_MODEL=Qwen_Qwen3.6-27B-Q5_K_L

:::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::

set LLM_TEMP=--temp 0.6 --top-k 20

set CTX_SIZE_OPTS= --ctx-size 10000

set VRAM_LOAD_OPTS= --fit-target 100 --n-gpu-layers 999
set REP_PENALITY_OPTS= --repeat-penalty 1.01 --repeat-last-n 8192
set MODEL_OPTS= -m models\%LL_MODEL%\%LL_MODEL%.gguf --alias "%LL_MODEL%"
set CHAT_TEMPL_OPTS= --jinja --chat-template-file models\%LL_MODEL%\chat_template.jinja
set MISC_OPTS= --port 11112 --log-colors off --no-mmap --parallel 1 -t 12

set THINK_OPTS= --reasoning-preserve --chat-template-kwargs "{\"preserve_thinking\":true}"
set GPU_OPTS= --split-mode tensor
set CACHE_PROMPT_OPTS= --cache-prompt --cache-ram 16384 --cache-reuse 8 -sps 0.8

:::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::

title %LL_MODEL% `%LLM_TEMP%` + cubetitled-ui
set path=D:\cpp\llama.cpp\cubetitled-ui\llama.cpp\build\bin\Release;%path%
llama-server.exe %MODEL_OPTS% %CHAT_TEMPL_OPTS% %VRAM_LOAD_OPTS% %CTX_SIZE_OPTS% %LLM_TEMP% %MISC_OPTS% %MTP_OPTS% %THINK_OPTS% %GPU_OPTS% %REP_PENALITY_OPTS% %CACHE_PROMPT_OPTS%

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions