journal de demarrage

etat/iquduwt33wwpvy.log

@@ -1,4 +1,4 @@
-=== bootstrap v84-nom-nemotron | 11:22:21 UTC ===
+=== bootstrap v84-nom-nemotron | 11:22:54 UTC ===
 [VL] 11:14:42 bootstrap v84-nom-nemotron
 [VL] 11:14:42 pilote 595.71.05, CUDA runtime 13.2
 [VL] 11:14:42 pilote 595.71.05 : compat CUDA non necessaire
@@ -16,6 +16,7 @@
 [VL] 11:15:51 cache de compilation, cle 94035774d7d7763f (NVIDIA_RTX_PRO_5000_Blackwell, vllm 0.27.1)
 [VL] 11:15:51 pas de cache pour cette cle : premiere compilation, il sera publie ensuite
 [VL] 11:15:51 journal distant : https://huggingface.co/patdev/k3-a40-bootstrap/resolve/main/etat/iquduwt33wwpvy.log
+[VL] 11:22:52 READY qwen38nvfp4
 
 === nvidia-smi ===
 41310 MiB, 48935 MiB
@@ -126,5 +127,52 @@
 (APIServer pid=5630) INFO 08-30 11:22:08 [api_server.py:678] Supported tasks: ['generate']
 (APIServer pid=5630) INFO 08-30 11:22:08 [parser_manager.py:37] "auto" tool choice has been enabled.
 (APIServer pid=5630) INFO 08-30 11:22:15 [hf.py:540] Detected the chat template content format to be 'openai'. You can set `--chat-template-content-format` to override this.
+(APIServer pid=5630) INFO 08-30 11:22:44 [base.py:235] Multi-modal warmup completed in 29.022s
+(APIServer pid=5630) INFO 08-30 11:22:45 [base.py:235] Readonly multi-modal warmup completed in 0.736s
+(APIServer pid=5630) WARNING 08-30 11:22:45 [model.py:1637] Default vLLM sampling parameters have been overridden by the model's `generation_config.json`: `{'temperature': 1.0, 'top_k': 20, 'top_p': 0.95}`. If this is not intended, please relaunch vLLM instance with `--generation-config vllm`.
+(APIServer pid=5630) INFO 08-30 11:22:46 [api_server.py:682] Starting vLLM server on http://0.0.0.0:18081
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:37] Available routes are:
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /openapi.json, Methods: HEAD, GET
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /docs, Methods: HEAD, GET
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /docs/oauth2-redirect, Methods: HEAD, GET
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /redoc, Methods: HEAD, GET
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /load, Methods: GET
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /version, Methods: GET
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /health, Methods: GET
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /metrics, Methods: GET
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /tokenize, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /detokenize, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /v1/models, Methods: GET
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /ping, Methods: GET
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /ping, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /invocations, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /v1/chat/completions, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /v1/chat/completions/batch, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /v1/responses, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /v1/responses/{response_id}, Methods: GET
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /v1/responses/{response_id}/cancel, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /v1/completions, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /v1/messages, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /v1/messages/count_tokens, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /generative_scoring, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /scale_elastic_ep, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /is_scaling_elastic_ep, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /v1/chat/completions/render, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /v1/completions/render, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /v1/chat/completions/derender, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /v1/completions/derender, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:46] Route: /inference/v1/generate, Methods: POST
+(APIServer pid=5630) INFO 08-30 11:22:46 [launcher.py:99] API server: waiting for HTTP server to start
+(APIServer pid=5630) INFO:     Started server process [5630]
+(APIServer pid=5630) INFO:     Waiting for application startup.
+(APIServer pid=5630) INFO:     Application startup complete.
+(APIServer pid=5630) INFO 08-30 11:22:47 [launcher.py:105] API server: HTTP server started
+(APIServer pid=5630) INFO:     127.0.0.1:58586 - "GET /health HTTP/1.1" 200 OK
+(APIServer pid=5630) INFO:     127.0.0.1:46254 - "GET /health HTTP/1.1" 200 OK
+(APIServer pid=5630) INFO:     127.0.0.1:46258 - "GET /health HTTP/1.1" 200 OK
 
 === proxy.log (fin) ===
+INFO:     Started server process [7771]
+INFO:     Waiting for application startup.
+INFO:     Application startup complete.
+INFO:     Uvicorn running on http://0.0.0.0:8088 (Press CTRL+C to quit)