[AMD] Update v4 args for agentic workload (#38677)

This commit is contained in:
Thomas Wang
2026-09-09 21:41:05 -07:00
committed by GitHub
parent 2f7393f0d2
commit c415f977b8
2 changed files with 5 additions and 3 deletions
@@ -2875,6 +2875,7 @@ sgl-eval run mmmu_pro \\
"--model-path {{MODEL_NAME}}",
"--tp 8",
"--attention-backend dsv4",
"--enable-deepseek-v4-fp4-indexer",
"--page-size 256",
"--mem-fraction-static 0.90",
"--swa-full-tokens-ratio 0.15",
@@ -2913,8 +2914,8 @@ sgl-eval run mmmu_pro \\
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--enable-deepseek-v4-fp4-indexer",
"--page-size 256",
"--mem-fraction-static 0.90",
"--swa-full-tokens-ratio 0.15",
@@ -2953,8 +2954,8 @@ sgl-eval run mmmu_pro \\
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--enable-deepseek-v4-fp4-indexer",
"--page-size 256",
"--mem-fraction-static 0.90",
"--swa-full-tokens-ratio 0.15",