vllm/benchmarks/attention_benchmarks/configs at 59a5cb387ae4c11c73855d505adb0b2c7cd3861d - vllm

Files

Matthew Bonanni e82fa448c4 Add attention benchmarking tools (#26835 )

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>

2026-01-28 00:09:20 +00:00

mla_decode.yaml

2026-01-28 00:09:20 +00:00

mla_mixed_batch.yaml

2026-01-28 00:09:20 +00:00

reorder_threshold.yaml

2026-01-28 00:09:20 +00:00

speculative_decode.yaml

2026-01-28 00:09:20 +00:00

standard_attention.yaml

2026-01-28 00:09:20 +00:00