52 lines
1.4 KiB
JSON
52 lines
1.4 KiB
JSON
{
|
|
"suite_id": "rs3_tiny_smoke",
|
|
"sim": "frontier_patched",
|
|
"frontier": {
|
|
"root": "/tmp/replayserve-frontier-rs1b",
|
|
"mode": "patched_scratch",
|
|
"patch": "patches/frontier-vllm-v1-prefix-cache-chunked-prefill.patch"
|
|
},
|
|
"fixtures": [
|
|
"coder_100"
|
|
],
|
|
"defaults": {
|
|
"simulation_mode": "online",
|
|
"sys_arch": "co-location",
|
|
"cluster_scheduler": "sticky_round_robin",
|
|
"replica_scheduler": "vllm_v1",
|
|
"model_name": "Qwen/Qwen3-32B",
|
|
"device": "a800",
|
|
"network_device": "a800_dgx",
|
|
"attn_tensor_parallel_size": 2,
|
|
"attn_data_parallel_size": 1,
|
|
"moe_tensor_parallel_size": 1,
|
|
"moe_expert_parallel_size": 1,
|
|
"num_pipeline_stages": 1,
|
|
"num_replicas": 1,
|
|
"batch_size_cap": 128,
|
|
"max_tokens_in_batch": 32768,
|
|
"block_size": 16,
|
|
"enable_prefix_caching": true,
|
|
"enable_chunked_prefill": true,
|
|
"long_prefill_token_threshold": 64,
|
|
"trace_max_tokens": 32768,
|
|
"num_blocks_mode": "memory_planner",
|
|
"gpu_memory_utilization": 0.9,
|
|
"non_kv_cache_overhead_bytes": 0,
|
|
"dummy_execution_time_ms": 1.0
|
|
},
|
|
"configs": [
|
|
{
|
|
"id": "fixed_prefix_on",
|
|
"description": "RS1 fixed config on patched Frontier scratch."
|
|
},
|
|
{
|
|
"id": "prefix_cache_off",
|
|
"description": "Diagnosis/control config with prefix cache disabled; all other fixed scheduler knobs unchanged.",
|
|
"overrides": {
|
|
"enable_prefix_caching": false
|
|
}
|
|
}
|
|
]
|
|
}
|