diff --git a/docs-site/static/sflow_intro.html b/docs-site/static/sflow_intro.html index 7445ed6..33b2da2 100644 --- a/docs-site/static/sflow_intro.html +++ b/docs-site/static/sflow_intro.html @@ -1174,10 +1174,10 @@

Structured Error Analysis

Model: DeepSeek R1 FP8 | 2 nodes × 8 GPUs | ISL=8192, OSL=1024 Allocation Map -├─ slurm-node-01 (node 0) +├─ node-01 (node 0) │ GPU 0-7: prefill_server_0 (TP=8) │ Also: load_image, nats, etcd, frontend, benchmark_* -└─ slurm-node-02 (node 1) +└─ node-02 (node 1) GPU 0-7: decode_server_0 (TP=8) Also: load_image, gpu_monitor @@ -1186,7 +1186,7 @@

Structured Error Analysis

01:59:10 — load_image COMPLETED on both nodes 01:59:43 — nats_server READY 01:59:45 — etcd_server READY -02:00:31 — frontend_server_0 READY (10.52.32.8) +02:00:31 — frontend_server_0 READY (10.x.x.x) 02:05:14 — prefill + decode READY → benchmark_4 starts 02:05:20 — HTTP 500 — all benchmark requests fail 02:05:41 — Workflow finished (8m 33s) diff --git a/docs-site/static/sflow_intro_zh.html b/docs-site/static/sflow_intro_zh.html index 2607bf0..56b927d 100644 --- a/docs-site/static/sflow_intro_zh.html +++ b/docs-site/static/sflow_intro_zh.html @@ -1174,10 +1174,10 @@

结构化的错误分析

Model: DeepSeek R1 FP8 | 2 nodes × 8 GPUs | ISL=8192, OSL=1024 Allocation Map -├─ slurm-node-01 (node 0) +├─ node-01 (node 0) │ GPU 0-7: prefill_server_0 (TP=8) │ Also: load_image, nats, etcd, frontend, benchmark_* -└─ slurm-node-02 (node 1) +└─ node-02 (node 1) GPU 0-7: decode_server_0 (TP=8) Also: load_image, gpu_monitor @@ -1186,7 +1186,7 @@

结构化的错误分析

01:59:10 — load_image COMPLETED on both nodes 01:59:43 — nats_server READY 01:59:45 — etcd_server READY -02:00:31 — frontend_server_0 READY (10.52.32.8) +02:00:31 — frontend_server_0 READY (10.x.x.x) 02:05:14 — prefill + decode READY → benchmark_4 starts 02:05:20 — HTTP 500 — all benchmark requests fail 02:05:41 — Workflow finished (8m 33s)