[AMD] Update v4 amd cookbook 0903 (#37829)

This commit is contained in:
Thomas Wang
2026-09-03 22:11:13 -07:00
committed by GitHub
parent ca7b8efd87
commit 225129fe44
2 changed files with 65 additions and 2 deletions
@@ -1828,6 +1828,10 @@ sgl-eval run mmmu_pro \\
"--tp 8",
"--dp 8",
"--enable-dp-attention",
"--enable-dp-attention-local-control-broadcast",
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--page-size 256",
@@ -1851,6 +1855,10 @@ sgl-eval run mmmu_pro \\
"--tp 8",
"--dp 8",
"--enable-dp-attention",
"--enable-dp-attention-local-control-broadcast",
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--page-size 256",
@@ -2607,6 +2615,10 @@ sgl-eval run mmmu_pro \\
"--tp 8",
"--dp 8",
"--enable-dp-attention",
"--enable-dp-attention-local-control-broadcast",
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--page-size 256",
@@ -2639,6 +2651,10 @@ sgl-eval run mmmu_pro \\
"--tp 8",
"--dp 8",
"--enable-dp-attention",
"--enable-dp-attention-local-control-broadcast",
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--page-size 256",
@@ -2675,6 +2691,10 @@ sgl-eval run mmmu_pro \\
"--tp 8",
"--dp 8",
"--enable-dp-attention",
"--enable-dp-attention-local-control-broadcast",
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--page-size 256",
@@ -2707,6 +2727,10 @@ sgl-eval run mmmu_pro \\
"--tp 8",
"--dp 8",
"--enable-dp-attention",
"--enable-dp-attention-local-control-broadcast",
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--page-size 256",
@@ -2774,6 +2798,10 @@ sgl-eval run mmmu_pro \\
"--tp 8",
"--dp 8",
"--enable-dp-attention",
"--enable-dp-attention-local-control-broadcast",
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--page-size 256",
@@ -2810,6 +2838,10 @@ sgl-eval run mmmu_pro \\
"--tp 8",
"--dp 8",
"--enable-dp-attention",
"--enable-dp-attention-local-control-broadcast",
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--page-size 256",
@@ -2877,6 +2909,10 @@ sgl-eval run mmmu_pro \\
"--tp 8",
"--dp 8",
"--enable-dp-attention",
"--enable-dp-attention-local-control-broadcast",
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--page-size 256",
@@ -2913,6 +2949,10 @@ sgl-eval run mmmu_pro \\
"--tp 8",
"--dp 8",
"--enable-dp-attention",
"--enable-dp-attention-local-control-broadcast",
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--page-size 256",
@@ -2980,6 +3020,10 @@ sgl-eval run mmmu_pro \\
"--tp 8",
"--dp 8",
"--enable-dp-attention",
"--enable-dp-attention-local-control-broadcast",
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--page-size 256",
@@ -3016,6 +3060,10 @@ sgl-eval run mmmu_pro \\
"--tp 8",
"--dp 8",
"--enable-dp-attention",
"--enable-dp-attention-local-control-broadcast",
"--tokenizer-worker-num 8",
"--stream-interval 20",
"--prefill-decode-interval 10",
"--enable-two-batch-overlap",
"--attention-backend dsv4",
"--page-size 256",