From fd1594bdbb233b1109b4f1ce2c54c7de04b90f89 Mon Sep 17 00:00:00 2001 From: ukannika Date: Tue, 2 Jun 2026 08:33:46 -0700 Subject: [PATCH 1/2] Update amd-master.yaml --- .github/configs/amd-master.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml index 1ad705468..f339a565f 100644 --- a/.github/configs/amd-master.yaml +++ b/.github/configs/amd-master.yaml @@ -1134,7 +1134,7 @@ gptoss-fp4-mi325x-vllm: gptoss-fp4-mi355x-vllm: image: vllm/vllm-openai-rocm:v0.22.0 - model: amd/gpt-oss-120b-w-mxfp4-a-fp8 + model: openai/gpt-oss-120b model-prefix: gptoss runner: mi355x precision: fp4 From a30921f45ed2180433923a66f654d3d37d7d9c26 Mon Sep 17 00:00:00 2001 From: Chun Fang Date: Fri, 5 Jun 2026 02:59:57 +0000 Subject: [PATCH 2/2] Add perf-changelog entry for #1638 Record the GPT-OSS MI355X vLLM model update (amd/gpt-oss-120b-w-mxfp4-a-fp8 -> openai/gpt-oss-120b). Co-authored-by: Cursor --- perf-changelog.yaml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/perf-changelog.yaml b/perf-changelog.yaml index a5f3f3478..dbf1282a1 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -3474,3 +3474,9 @@ - "Use scheduler-recv-interval values 2/60/30/1200/600/1920 for conc 1-4/8/16/32/64/128-256" - "Set max-running-requests=256, chunked-prefill-size=16384, mem-fraction-static=0.8, cuda-graph-max-bs=CONC, and enable symm-mem" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1544 + +- config-keys: + - gptoss-fp4-mi355x-vllm + description: + - "Update GPT-OSS model for MI355X vLLM from amd/gpt-oss-120b-w-mxfp4-a-fp8 to openai/gpt-oss-120b" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1638