From ea0a99db217149f55237a02b86bf48fc882ac9c0 Mon Sep 17 00:00:00 2001 From: functionstackx <47992694+functionstackx@users.noreply.github.com> Date: Sun, 17 May 2026 22:15:43 -0400 Subject: [PATCH 1/2] Update kimik2.5-int4-mi325x-vllm vLLM ROCm image to v0.21.0 Update vLLM ROCm image from v0.18.0 (52d old) to v0.21.0 Co-Authored-By: Claude Opus 4.7 (1M context) --- .github/configs/amd-master.yaml | 2 +- perf-changelog.yaml | 6 ++++++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml index 75a70bcf1..d78f6b714 100644 --- a/.github/configs/amd-master.yaml +++ b/.github/configs/amd-master.yaml @@ -527,7 +527,7 @@ kimik2.5-int4-mi355x-vllm: - { tp: 8, conc-start: 4, conc-end: 64 } kimik2.5-int4-mi325x-vllm: - image: vllm/vllm-openai-rocm:v0.18.0 + image: vllm/vllm-openai-rocm:v0.21.0 model: moonshotai/Kimi-K2.5 model-prefix: kimik2.5 runner: mi325x diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 2bdf9f729..54d3cc171 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -2653,3 +2653,9 @@ description: - "Update SGLang image from v0.5.9-cu129-amd64 (74d old) to v0.5.12-cu130" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1458 + +- config-keys: + - kimik2.5-int4-mi325x-vllm + description: + - "Update vLLM ROCm image from v0.18.0 (52d old) to v0.21.0" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX From c352665b9438cc98937f88feaafa32d260ac79b0 Mon Sep 17 00:00:00 2001 From: functionstackx <47992694+functionstackx@users.noreply.github.com> Date: Sun, 17 May 2026 22:15:47 -0400 Subject: [PATCH 2/2] chore: fill pr-link for #1468 --- perf-changelog.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 54d3cc171..65cce9f0f 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -2658,4 +2658,4 @@ - kimik2.5-int4-mi325x-vllm description: - "Update vLLM ROCm image from v0.18.0 (52d old) to v0.21.0" - pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1468