From a7b3c06f3bd0981dd000c62b90232bda0fb4053a Mon Sep 17 00:00:00 2001 From: liusy58 Date: Sat, 22 Aug 2026 11:06:31 +0800 Subject: [PATCH] fix --- blog/2026-08-21-sglang-fast-recovery.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/blog/2026-08-21-sglang-fast-recovery.md b/blog/2026-08-21-sglang-fast-recovery.md index cc17c79e1..c19116e93 100644 --- a/blog/2026-08-21-sglang-fast-recovery.md +++ b/blog/2026-08-21-sglang-fast-recovery.md @@ -34,7 +34,7 @@ Where does the time go? We profiled a complete SGLang engine startup for Ling-2. |-------|----------|------------|-------| | Pre-init & ServerArgs | ~1 | 0.2% | Pre-init and ServerArgs parsing | | Tokenizer init | ~13 | 2.4% | load and init tokenizer | -| Init torch distributed | ~5 | 0.9% | NCCL 2.28.9,8 卡 H20,NVLink mesh 370.8 GB/s,P2P/IPC;slowest rank TP1=5.19s | +| Init torch distributed | ~5 | 0.9% | NCCL 2.28.9,8*H20,NVLink mesh 370.8 GB/s,P2P/IPC;slowest rank TP1=5.19s | | Load weight (disk) | ~495 | 93.9% | 161 shard,W8A8 FP8 (CompressedTensorsW8A8Fp8MoE),slowest rank=495.3s, 120GB per card; Disk I/O bound | | Cache allocation (KV+Mamba) | ~1 | 0.2% | KV:553,599 tokens/5.94GB bf16;Mamba SSM state:5.33GB,max_mamba_cache_size=155 | | Capture CUDA graph | ~7.7 | 1.5% | only 3 decode BS [1,2,4] |