23 lines
1.2 KiB
JSON
23 lines
1.2 KiB
JSON
{
|
|
"observation": "Long-context chat traffic is dominated by large prefills, so TTFT under the stepped SLO is the binding constraint. A launch-safe baseline should spread compute across all 4 GPUs while limiting concurrent long-prefill contention.",
|
|
"diagnosis": "The FLASHINFER attempt failed at startup, but the safer FLASH_ATTN family launched successfully. A conservative seq cap plus a moderate batched-token cap is a better baseline for diagnosing whether the SLO itself is too aggressive under this trace.",
|
|
"config_patch": {
|
|
"env_patch": {
|
|
"VLLM_ATTENTION_BACKEND": "FLASH_ATTN"
|
|
},
|
|
"flag_patch": {
|
|
"tensor-parallel-size": 4,
|
|
"max-num-seqs": 16,
|
|
"max-num-batched-tokens": 24576,
|
|
"gpu-memory-utilization": 0.94,
|
|
"block-size": 32
|
|
}
|
|
},
|
|
"expected_effects": [
|
|
"Stable 4-GPU launch without FLASHINFER warmup failure",
|
|
"Lower head-of-line blocking than larger sequence caps",
|
|
"More interpretable lower-bound throughput/SLO measurement"
|
|
],
|
|
"why_not_previous_failures": "This proposal keeps the launch-safe FLASH_ATTN backend and the conservative batching limits that already avoided the earlier FLASHINFER startup failure."
|
|
}
|