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)

compose.yaml

@@ -183,7 +183,7 @@ services:
     env_file: envs/.env.smollm3-3b-bigctx
     healthcheck:
       <<: *hc
-      start_period: 60s
+      start_period: 90s
 
   llama-gemma4-e2b-bigctx:
     image: local/llama-cpp-turboquant:server-cuda-sm75-mmq
@@ -192,7 +192,7 @@ services:
     env_file: envs/.env.gemma4-e2b-bigctx
     healthcheck:
       <<: *hc
-      start_period: 60s
+      start_period: 120s  # large ctx (393216) allocation takes extra time
 
   llama-gemma4-e4b-bigctx:
     image: local/llama-cpp-turboquant:server-cuda-sm75-mmq
@@ -201,7 +201,7 @@ services:
     env_file: envs/.env.gemma4-e4b-bigctx
     healthcheck:
       <<: *hc
-      start_period: 60s
+      start_period: 150s  # 5 GiB model + warmup + 163840 ctx takes ~90-120s
 
   llama-qwen3-4b-bigctx:
     image: local/llama-cpp-turboquant:server-cuda-sm75-mmq
@@ -210,7 +210,7 @@ services:
     env_file: envs/.env.qwen3-4b-bigctx
     healthcheck:
       <<: *hc
-      start_period: 60s
+      start_period: 90s
 
   # ── OPEN WEBUI ─────────────────────────────────────────────────────────────
   # Separate profile — add to any running model: