diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml index 0a6c86df6..8c880b8a8 100644 --- a/configs/nvidia-master.yaml +++ b/configs/nvidia-master.yaml @@ -8991,7 +8991,7 @@ glm5.2-fp4-b300-sglang-agentic-mtp: image: lmsysorg/sglang:v0.5.16-cu130 model: nvidia/GLM-5.2-NVFP4 model-prefix: glm5.2 - runner: cluster:b300-nv + runner: cluster:b300-dsxe precision: fp4 framework: sglang multinode: false @@ -8999,7 +8999,7 @@ glm5.2-fp4-b300-sglang-agentic-mtp: agentic-coding: - dram-utilization: 0.80 search-space: - - { tp: 8, spec-decoding: mtp, kv-offloading: dram, kv-offload-backend: { name: hicache }, conc-list: [1, 4, 8, 12, 16] } + - { tp: 8, spec-decoding: mtp, kv-offloading: dram, kv-offload-backend: { name: hicache }, conc-list: [1, 4, 8, 12, 16, 20, 24, 28, 32, 40, 48] } # First GLM-5.2 AgentX recipe on B200, shipped spec-decode-only per the AgentX # policy that agentic arms enable speculative decoding rather than running a diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 14434c76a..5386da981 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -6878,3 +6878,12 @@ description: - "Refresh the Kimi-K3 GB300 AgentX configurations with updated configs." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2811 + +- config-keys: + - glm5.2-fp4-b300-sglang-agentic-mtp + scenario-type: + - agentic-coding + description: + - "Extend the GLM-5.2 NVFP4 B300 SGLang AgentX MTP TP8 HiCache curve from concurrency 16 to 48 with new points at 20, 24, 28, 32, 40, and 48." + - "Move the recipe from the retired cluster:b300-nv fleet to cluster:b300-dsxe so the sweep can be generated and scheduled again." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2829