From f55586f8fedd78c20ddf208c2b2e934ca1010135 Mon Sep 17 00:00:00 2001 From: hjjq <50634613+hjjq@users.noreply.github.com> Date: Tue, 23 Jun 2026 08:31:17 -0700 Subject: [PATCH 1/2] bump --- .../vllm/deepseek-v4/8k1k/disagg-b200-low-latency.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4/8k1k/disagg-b200-low-latency.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4/8k1k/disagg-b200-low-latency.yaml index 2a449451b4..89f3f2741f 100644 --- a/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4/8k1k/disagg-b200-low-latency.yaml +++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4/8k1k/disagg-b200-low-latency.yaml @@ -17,7 +17,7 @@ name: "svf-vllm-disagg-b200-low-latency" # absorb cold-cache model loads. model: path: "deepseek-v4-pro" - container: "vllm/vllm-openai:v0.20.1" + container: "vllm/vllm-openai:v0.23.0" precision: "fp4" dynamo: @@ -131,7 +131,7 @@ benchmark: identity: container: - image: "vllm/vllm-openai:v0.20.1" + image: "vllm/vllm-openai:v0.23.0" frameworks: dynamo: "1.2.0.dev20260426" vllm: "0.20.0" From e821fa1545730ab5cadc7e01586ab6da2d601822 Mon Sep 17 00:00:00 2001 From: hjjq <50634613+hjjq@users.noreply.github.com> Date: Tue, 23 Jun 2026 08:36:32 -0700 Subject: [PATCH 2/2] fix --- .../vllm/deepseek-v4/8k1k/disagg-b200-low-latency.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4/8k1k/disagg-b200-low-latency.yaml b/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4/8k1k/disagg-b200-low-latency.yaml index 89f3f2741f..7549794136 100644 --- a/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4/8k1k/disagg-b200-low-latency.yaml +++ b/benchmarks/multi_node/srt-slurm-recipes/vllm/deepseek-v4/8k1k/disagg-b200-low-latency.yaml @@ -134,4 +134,4 @@ identity: image: "vllm/vllm-openai:v0.23.0" frameworks: dynamo: "1.2.0.dev20260426" - vllm: "0.20.0" + vllm: "0.23.0"