|
9963 | 9963 | - dsv41flash-fp4-gb200-sglang-agentic-dspark |
9964 | 9964 | - dsv41flash-fp4-gb300-vllm-agentic-dspark |
9965 | 9965 | - dsv41flash-fp4-gb300-sglang-agentic-dspark |
| 9966 | + - qwen3.5-fp8-gb300-dynamo-sglang-agentic-pp-pareto |
| 9967 | + - qwen3.5-fp8-gb300-dynamo-sglang-agentic-agg-pareto |
| 9968 | + - qwen3.5-fp8-gb300-dynamo-sglang-agentic-pp-midcurve |
| 9969 | + - qwen3.5-fp8-gb300-dynamo-sglang-agentic-agg-midcurve |
| 9970 | + - dsv4-fp4-gb200-dynamo-sglang-agentic-agg |
| 9971 | + - dsv4-fp4-gb200-dynamo-sglang-agentic-disagg |
| 9972 | + - dsv41flash-fp4-gb300-dynamo-sglang-agentic-agg |
| 9973 | + - dsv41flash-fp4-gb300-dynamo-sglang-agentic-disagg |
| 9974 | + - dsv41flash-fp4-gb300-dynamo-vllm-agentic-dspark-agg |
| 9975 | + - dsv41flash-fp4-gb300-dynamo-vllm-agentic-dspark-disagg |
| 9976 | + - dsv4-fp4-gb200-dynamo-vllm-agentic-dspark-agg |
| 9977 | + - dsv4-fp4-gb200-dynamo-vllm-agentic-dspark-disagg |
| 9978 | + - qwen3.8next-fp4-gb300-sglang-agentic-mtp |
| 9979 | + - kimik3-fp4-h200-vllm-agentic-latency |
| 9980 | + - kimik3-fp4-h200-vllm-agentic-balanced |
| 9981 | + - kimik3-fp4-h200-vllm-agentic-simple |
| 9982 | + - dsv4-fp8-h200-dynamo-sglang-agentic-agg |
| 9983 | + - glm5.2-fp8-h200-dynamo-sglang-agentic-mtp-2p2d |
| 9984 | + - glm5.2-fp8-h200-dynamo-sglang-agentic-mtp-1p1d-hicache |
| 9985 | + - glm5.2-fp8-h200-dynamo-sglang-agentic-mtp-agg |
| 9986 | + - kimik3-fp4-b200-dynamo-vllm-agentic-dspark |
| 9987 | + - qwen3.5-fp8-b200-dynamo-sglang-agentic-disagg-mtp |
9966 | 9988 | description: |
9967 | 9989 | - "Enable best-effort noprof GPU and ACPI Grace CPU collection by default for GB200/GB300 benchmarks, including native single-node and AgentX, with the pinned cpu-power-exporter v2.51.1. Explicit required-power AgentX points fail on invalid GPU or expected CPU evidence; ordinary points retain valid benchmark results and independent GPU/CPU validity. Eval-only jobs omit collection." |
9968 | 9990 | - "Place benchmark clients and telemetry on the head clock without changing worker or allocation counts. Native single-node results retain their real topology and power audit. Placement changes require fresh performance results." |
9969 | | - - "Require validated power on the 11 GLM-5.2 GB200 aggregate/disaggregated/MTP AgentX points and 24 DSV4 GB200 aggregate MTP TP8/DEP8 points, retaining their current images, selectors and topology." |
| 9991 | + - "Require validated power on the 11 GLM-5.2 GB200 aggregate/disaggregated/MTP AgentX points and 24 DSV4 GB200 aggregate MTP TP8/DEP8 points. Declare the five existing Kimi-K3 GB200/GB300 measured-power arms strict in their matrix rows instead of a cluster-wide Kimi rule. Retain their current images, selectors and topology." |
| 9992 | + - "Forward the selected required-power flag through existing H200/B200 AgentX clients, telemetry, and result collection. Align the Qwen3.8-Next GB300 recipe's declared host DRAM with the current runner's 241 GB allowance while retaining its H224 cache setting." |
9970 | 9993 | pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/3670 |
0 commit comments