From f40f14fecb67c0db1ac7e6196a7b28607ecc4f7d Mon Sep 17 00:00:00 2001 From: Ankur-singh Date: Thu, 28 May 2026 10:42:23 -0700 Subject: [PATCH 1/2] kimik2.5-fp4-gb200-dynamo-vllm: bump vllm image to v0.21.0 Bumps the kimik2.5-fp4-gb200-dynamo-vllm image from vllm/vllm-openai:v0.18.0-cu130 to vllm/vllm-openai:v0.21.0. --- .github/configs/nvidia-master.yaml | 2 +- perf-changelog.yaml | 7 +++++++ 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml index f8cc486b2..c7c92a700 100644 --- a/.github/configs/nvidia-master.yaml +++ b/.github/configs/nvidia-master.yaml @@ -8270,7 +8270,7 @@ kimik2.5-fp4-gb200-dynamo-trt: dp-attn: true kimik2.5-fp4-gb200-dynamo-vllm: - image: vllm/vllm-openai:v0.18.0-cu130 + image: vllm/vllm-openai:v0.21.0 model: nvidia/Kimi-K2.5-NVFP4 model-prefix: kimik2.5 runner: gb200 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index b7182a39c..b71650fea 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -3192,3 +3192,10 @@ - "Add GLM-5-FP8 models.yaml flags, setup_deps.sh (aiter gluon + transformers glm_moe_dsa), GLM-5 env tuning in env.sh" - "Add multinode launch script glm5_fp8_mi355x_sglang-disagg.sh; server.sh sources setup_deps.sh" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1572 + +- config-keys: + - kimik2.5-fp4-gb200-dynamo-vllm + description: + - "Bump vLLM image from vllm/vllm-openai:v0.18.0-cu130 to vllm/vllm-openai:v0.21.0" + pr-link: TBD + From 424a2946609cc64210c3812a7c758abf3e444af8 Mon Sep 17 00:00:00 2001 From: Ankur-singh Date: Thu, 28 May 2026 10:42:42 -0700 Subject: [PATCH 2/2] perf-changelog: set PR link to #1582 --- perf-changelog.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/perf-changelog.yaml b/perf-changelog.yaml index b71650fea..25ac8f78f 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -3197,5 +3197,5 @@ - kimik2.5-fp4-gb200-dynamo-vllm description: - "Bump vLLM image from vllm/vllm-openai:v0.18.0-cu130 to vllm/vllm-openai:v0.21.0" - pr-link: TBD + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1582