journal de demarrage

etat/xtn8ts2meqsqb4.log

@@ -1,4 +1,4 @@
-=== bootstrap v86-journal-runtime-continu | 00:10:05 UTC ===
+=== bootstrap v86-journal-runtime-continu | 00:12:08 UTC ===
 [VL] 23:36:01 bootstrap v86-journal-runtime-continu
 [VL] 23:36:01 pilote 595.91.07, CUDA runtime 13.2
 [VL] 23:36:01 pilote 595.91.07 : compat CUDA non necessaire
@@ -295,6 +295,13 @@
 (APIServer pid=5703) INFO 09-06 00:08:23 [loggers.py:310] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 9.5 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 19.0%
 (APIServer pid=5703) INFO 09-06 00:08:23 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 1.00, Accepted throughput: 0.00 tokens/s, Drafted throughput: 28.50 tokens/s, Accepted: 0 tokens, Drafted: 285 tokens, Per-position acceptance rate: 0.000, 0.000, 0.000, Avg Draft acceptance rate: 0.0%
 (APIServer pid=5703) INFO 09-06 00:08:33 [loggers.py:310] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 10.3%, Prefix cache hit rate: 20.3%
+(APIServer pid=5703) INFO 09-06 00:10:23 [loggers.py:310] Engine 000: Avg prompt throughput: 24239.5 tokens/s, Avg generation throughput: 31.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 24.1%, Prefix cache hit rate: 20.3%
+(APIServer pid=5703) INFO 09-06 00:10:23 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 1.00, Accepted throughput: 0.00 tokens/s, Drafted throughput: 7.82 tokens/s, Accepted: 0 tokens, Drafted: 939 tokens, Per-position acceptance rate: 0.000, 0.000, 0.000, Avg Draft acceptance rate: 0.0%
+(APIServer pid=5703) INFO:     172.71.134.75:0 - "POST /v1/messages/count_tokens?beta=true HTTP/1.1" 200 OK
+(APIServer pid=5703) INFO:     172.71.134.75:0 - "POST /v1/messages?beta=true HTTP/1.1" 200 OK
+(APIServer pid=5703) INFO 09-06 00:10:33 [loggers.py:310] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 13.5 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 20.3%
+(APIServer pid=5703) INFO 09-06 00:10:33 [metrics.py:120] SpecDecoding metrics: Mean acceptance length: 1.00, Accepted throughput: 0.00 tokens/s, Drafted throughput: 40.50 tokens/s, Accepted: 0 tokens, Drafted: 405 tokens, Per-position acceptance rate: 0.000, 0.000, 0.000, Avg Draft acceptance rate: 0.0%
+(APIServer pid=5703) INFO 09-06 00:10:43 [loggers.py:310] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 10.3%, Prefix cache hit rate: 21.3%
 
 === proxy.log (fin) ===
 INFO:     Started server process [6819]
@@ -317,3 +324,5 @@ INFO:     100.64.1.5:49334 - "POST /v1/messages?beta=true HTTP/1.1" 200 OK
 INFO:     100.64.1.2:43518 - "POST /v1/messages?beta=true HTTP/1.1" 200 OK
 INFO:     100.64.1.1:54690 - "POST /v1/messages?beta=true HTTP/1.1" 200 OK
 INFO:     100.64.1.3:38406 - "POST /v1/messages?beta=true HTTP/1.1" 200 OK
+INFO:     100.64.1.3:38406 - "POST /v1/messages/count_tokens?beta=true HTTP/1.1" 200 OK
+INFO:     100.64.1.3:38406 - "POST /v1/messages?beta=true HTTP/1.1" 200 OK