Skip to content
End-to-End Tests

e2e Test - minimax h200 aiperf #2603

Sign in to view logs

e2e Test - minimax h200 aiperf

e2e Test - minimax h200 aiperf #2603

Run time

Learn about OS pricing on GitHub Actions
Job Run time
get-jobs
10s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc32_offloadnone fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-32
46m 23s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc24_offloadnone fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-24
46m 43s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc28_offloadcpu fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-28
47m 21s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc16_offloadnone fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-16
45m 16s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc48_offloadnone fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-48
48m 4s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc4_offloadnone fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-4
43m 9s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc24_offloadcpu fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-24
47m 2s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc8_offloadnone fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-8
44m 0s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc1_offloadnone fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-1
38m 24s
multi-node /
0s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc40_offloadcpu fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-40
48m 7s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc36_offloadcpu fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-36
59m 38s
multi-node eval /
0s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc36_offloadnone fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-36
46m 57s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc28_offloadnone fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-28
46m 26s
single-node /
0s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc2_offloadnone fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-2
42m 45s
multi-node agentic /
0s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc48_offloadcpu fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-48
59m 21s
agentic / (vllm/vllm-openai:v0.21.0, MiniMaxAI/MiniMax-M2.5, minimaxm2.5, fp8, vllm, h200, 4, 1, ... / minimaxm2.5_tp4_conc32_offloadcpu fp8 h200 vllm | tp=4 ep=1 dpa=false | disagg-false spec-none conc-32
36m 44s
eval /
0s
collect-evals
0s
collect-agentic-results
21s
collect-results / collect-results
15s
calc-success-rate
18s
12h 27m 24s