@troed@fedia.io
in
localllama
·
4d ago
troed
@troed@fedia.io
HW/FW security researcher & Demoscene elder. I started having arguments online back on Fidonet and Usenet. I'm too tired to care now.
fedia.io
Opencode llama-server prefill/generation stats plugin
Opencode llama-server prefill/generation stats plugin #opencode #llama
Hover or focus to reveal
Sensitive
I've just published an Opencode plugin I made since I couldn't find one that fulfilled the exact use case I had myself. Publishing and posting in case it's useful for someone else too.
When working with local models I have the need to know why there's suddenly nothing happening (besides the blue cylon-bar) but the plugins I found only showed token generation data when something was passed into Opencode. That meant that during >1 minute prefills there was no output at all.
This plugin uses the /slots endpoint (enabled by default) in llama-server to deduce whether it's currently generating tokens or doing prompt processing, and also the current tps for that activity. Now I can just run llama-server as a daemon and I no longer feel the need to go inspect its output just to see what's up.
It's likely only useful in a single-user scenario, but it has been tested with both single and multiple parallel slots.
Installation:
opencode plugin @troed/oc-ls-stats@latest --global
0
1
0
@skerit@mastodon.elevenways.be
·
Feb 24, 2026
Jelle De Loecker
@skerit@mastodon.elevenways.be
Co-founder of https://elevenways.be digital accessibility lab Married to @roel Programmer, mainly for the web in JavaScript Owner of the https://blackblock.rocks Minecraft server #linux #a11y #development #javascript #minecraft #gaming #fedi22 #lgbtq+
mastodon.elevenways.be
Every time I see Claude/Gemini/… use git stash to “check if a certain test failure is pre-existing” I hold my breath, because that has gone wrong quite a few times before.
1
0
0
@GavinCampbell@hometech.social
·
Feb 13, 2026
Gavin Campbell
@GavinCampbell@hometech.social
HomeTech.fm Co-Host. I toot about Home Tech, Home Automation, Basketball, Golf, Reggae, Configuration Manager and TV shows.
hometech.social
So I’ve gone full circle with my AI coding flow.
I started wirh OpenCode, but decided to try Codex and then moved over to Claude Code.
I’m now back with OpenCode but have my agents using models from two different services to balance out the load based on their strength.
I feel like this is the way it should be. Thoughts?
#OpenCode #ClaudeCode #Codex #Anthropic #OpenAI
0
1
0
You've seen all posts