me/env-ansible
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

llm, enhance comments in the ollama run script.

Browse Source
This commit is contained in:
me
2026-10-09 20:06:14 -07:00
parent 4ce0720a43
commit 6735e257b3
1 changed files with 10 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tasks/workstation/linux/software/llm.yml
+10 -5
View File
@@ -182,20 +182,25 @@
dest: "{{ ollama_runit_script }}" dest: "{{ ollama_runit_script }}"
content: | content: |
#!/bin/sh -e #!/bin/sh -e
# Allow pulling LLMs for use with ZeroClaw. # Allow pulling and accessing LLMs via tools.
exec 2>&1 exec 2>&1
### Required ###
export HOME={{ user_user.home }} export HOME={{ user_user.home }}
# Timeouts # ### Timeouts ###
export OLLAMA_LOAD_TIMEOUT=20m # default is 5m export OLLAMA_LOAD_TIMEOUT=20m # default is 5m
export OLLAMA_REQUEST_TIMEOUT=3600 # default 300 (unconfirmed, not in the list of --help vars) export OLLAMA_REQUEST_TIMEOUT=3600 # default 300 (unconfirmed, not in the list of --help vars)
# Resource Usage # ### Resource Usage ###
export OLLAMA_KEEP_ALIVE=20m # default is 5m export OLLAMA_KEEP_ALIVE=20m # default is 5m
export OLLAMA_MAX_LOADED_MODELS={{ llm_concurrency }} # default is 3 if using CPUs, or 3 * NumGPUs export OLLAMA_MAX_LOADED_MODELS={{ llm_concurrency }} # default is 3 if using CPUs, or 3 * NumGPUs
export OLLAMA_NUM_PARALLEL={{ llm_parallel }} # default is 1 and applies per-model (unconfirmed) export OLLAMA_NUM_PARALLEL={{ llm_parallel }} # default is 1 and applies per-model (unconfirmed)
export OLLAMA_CONTEXT_LENGTH={{ llm_context }} # default is 4096, https://docs.ollama.com/faq#how-can-i-specify-the-context-window-size export OLLAMA_CONTEXT_LENGTH={{ llm_context }} # default is 4096, https://docs.ollama.com/faq#how-can-i-specify-the-context-window-size
export OLLAMA_MAX_QUEUE=999 # default is 512 (unconfirmed) export OLLAMA_MAX_QUEUE=999 # default is 512 (unconfirmed)
# Prevent Data Loss # ### Prevent Data Loss ###
export OLLAMA_NOPRUNE=1 # Default is 0, which causes unfinished pulls to be deleeted after 1 hour. (unconfirmed) # OLLAMA_NOPRUNE
# Default is 0, which causes unfinished pulls to be deleted
# after 1 hour of inactivity. To manually clean partials, run:
# `rm ~/.ollama/models/blobs/*-partial*`
export OLLAMA_NOPRUNE=1
exec chpst -u {{ user }} ollama serve exec chpst -u {{ user }} ollama serve
mode: "0755" mode: "0755"