Upload etat/vie-fcbniqxcbq2uq0.log with huggingface_hub
Browse files
etat/vie-fcbniqxcbq2uq0.log
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
-
[VIE] 19:
|
| 2 |
NVIDIA RTX PRO 6000 Blackwell Server Edition, 96612 MiB, 97887 MiB, 0 %
|
| 3 |
RAM conteneur : 238.3 / 251.0 Go (cgroup)
|
| 4 |
disque / : 101 Go libres sur 236
|
| 5 |
poids telecharges : 135.3 / 125.9 Go (107 %) (a l'arret : 0.00 Go/min)
|
| 6 |
-
python3 6.8% 101.1Go | VLLM::Worker 121% 3.3Go | vllm 3.5% 2.0Go | VLLM::EngineCor
|
| 7 |
--- dl.log ---
|
| 8 |
Fetching 419 files: 99%|█████████▉| 416/419 [12:54<00:46, 15.55s/it]
|
| 9 |
Fetching 419 files: 100%|█████████▉| 417/419 [12:55<00:24, 12.23s/it]
|
|
@@ -12,9 +12,9 @@ Fetching 419 files: 100%|██████████| 419/419 [12:56<00:00,
|
|
| 12 |
Fetching 419 files: 100%|██████████| 419/419 [12:56<00:00, 1.85s/it]
|
| 13 |
TELECHARGE en 777 s -> /root/.cache/huggingface/hub/models--RadixArk--Qwen3.8-Flash-Next-NVFP4/snapshots/7b719225242aacd3dbd3f9407468c2ee9a9d2594
|
| 14 |
--- vllm.log ---
|
| 15 |
-
(APIServer pid=14538) INFO 08-27 19:04:50 [loggers.py:310] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 93.6%
|
| 16 |
-
(APIServer pid=14538) INFO: 127.0.0.1:55966 - "GET /metrics HTTP/1.1" 200 OK
|
| 17 |
(APIServer pid=14538) INFO: 127.0.0.1:52206 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
| 18 |
(APIServer pid=14538) INFO 08-27 19:05:30 [loggers.py:310] Engine 000: Avg prompt throughput: 1.3 tokens/s, Avg generation throughput: 0.8 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 93.6%
|
| 19 |
(APIServer pid=14538) INFO: 127.0.0.1:52222 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
| 20 |
(APIServer pid=14538) INFO 08-27 19:05:40 [loggers.py:310] Engine 000: Avg prompt throughput: 1.3 tokens/s, Avg generation throughput: 0.8 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 93.6%
|
|
|
|
|
|
|
|
|
| 1 |
+
[VIE] 19:06:02 pod=fcbniqxcbq2uq0
|
| 2 |
NVIDIA RTX PRO 6000 Blackwell Server Edition, 96612 MiB, 97887 MiB, 0 %
|
| 3 |
RAM conteneur : 238.3 / 251.0 Go (cgroup)
|
| 4 |
disque / : 101 Go libres sur 236
|
| 5 |
poids telecharges : 135.3 / 125.9 Go (107 %) (a l'arret : 0.00 Go/min)
|
| 6 |
+
python3 6.8% 101.1Go | VLLM::Worker 121% 3.3Go | vllm 3.5% 2.0Go | VLLM::EngineCor 68.9% 1.5Go | python3 0.6% 0.3Go |
|
| 7 |
--- dl.log ---
|
| 8 |
Fetching 419 files: 99%|█████████▉| 416/419 [12:54<00:46, 15.55s/it]
|
| 9 |
Fetching 419 files: 100%|█████████▉| 417/419 [12:55<00:24, 12.23s/it]
|
|
|
|
| 12 |
Fetching 419 files: 100%|██████████| 419/419 [12:56<00:00, 1.85s/it]
|
| 13 |
TELECHARGE en 777 s -> /root/.cache/huggingface/hub/models--RadixArk--Qwen3.8-Flash-Next-NVFP4/snapshots/7b719225242aacd3dbd3f9407468c2ee9a9d2594
|
| 14 |
--- vllm.log ---
|
|
|
|
|
|
|
| 15 |
(APIServer pid=14538) INFO: 127.0.0.1:52206 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
| 16 |
(APIServer pid=14538) INFO 08-27 19:05:30 [loggers.py:310] Engine 000: Avg prompt throughput: 1.3 tokens/s, Avg generation throughput: 0.8 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 93.6%
|
| 17 |
(APIServer pid=14538) INFO: 127.0.0.1:52222 - "POST /v1/chat/completions HTTP/1.1" 200 OK
|
| 18 |
(APIServer pid=14538) INFO 08-27 19:05:40 [loggers.py:310] Engine 000: Avg prompt throughput: 1.3 tokens/s, Avg generation throughput: 0.8 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 93.6%
|
| 19 |
+
(APIServer pid=14538) INFO 08-27 19:05:50 [loggers.py:310] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 93.6%
|
| 20 |
+
(APIServer pid=14538) INFO: 127.0.0.1:59916 - "GET /metrics HTTP/1.1" 200 OK
|