mozempk/llama-cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
6 Commits 1 Branch 0 Tags
master
Commit Graph

4 Commits

Author SHA1 Message Date
Giancarmine Salucci
e7e389c0e1 llama+compose: fix bigctx startup timing 
- compose: increase start_period for bigctx services
  - gemma4-e4b-bigctx: 60s -> 150s (5 GiB model + warmup + 163840 ctx takes ~90-120s)
  - gemma4-e2b-bigctx: 60s -> 120s (large ctx 393216 allocation)
  - smollm3/qwen3-4b bigctx: 60s -> 90s
- llama: extend health poll from 30x2s=60s to 75x2s=150s
- llama: require 3 consecutive unhealthy before giving up (avoids
  false positives during Docker start_period window)
 2026-05-06 19:03:31 +02:00
Giancarmine Salucci
0618078937 llama: fix bigctx double-profile conflict (llama_server name collision) 2026-05-06 17:41:20 +02:00
Giancarmine Salucci
33333507a5 llama: remove stopped containers before start to fix name conflict 2026-05-06 17:37:47 +02:00
Giancarmine Salucci
9f0193c3fc Add llama launcher script 
- ./llama (interactive menu) or ./llama <cmd> [args]
- start <model> [--bigctx] [--webui]: verify model file, warn before stopping running server, health-wait after start
- stop: stop all llama containers
- status: running model + health + env vars
- logs [--follow]: tail server logs
- build: build TurboQuant images
- bench <model>: run llama-bench via bench profile
 2026-05-06 17:31:35 +02:00