gahow/replaysim
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add ReplayServe Frontier vLLM alignment report

Browse Source
This commit is contained in:
Gahow Wang
2026-06-25 17:10:30 +08:00
commit a99bd00782
63 changed files with 17033 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
configs/rs10_frontier_h20_tp1_profile_full32k_coder200_ts2_ts3.json Normal file
View File

@@ -0,0 +1,60 @@
{
"suite_id": "rs10_frontier_h20_tp1_profile_full32k_coder200_ts2_ts3",
"sim": "frontier_h20_tp1_profile_full32k",
"frontier": {
"root": "/tmp/replayserve-frontier-rs1b",
"mode": "patched_scratch",
"patches": [
"patches/frontier-vllm-v1-prefix-cache-chunked-prefill.patch",
"patches/frontier-vllm-0.11.1-profiling-compat.patch"
],
"profile_source": "dash2:/home/admin/cpfs/wjh/replayserve_frontier_profiles/h20_tp1_qwen3_30ba3b_full32k_20260624"
},
"fixtures": [
"coder_200_ts2",
"coder_200_ts3"
],
"defaults": {
"simulation_mode": "online",
"sys_arch": "co-location",
"cluster_scheduler": "sticky_round_robin",
"replica_scheduler": "vllm_v1",
"model_name": "qwen3-a3b-30b-moe",
"device": "h20",
"network_device": "h20_dgx",
"attn_tensor_parallel_size": 1,
"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": 64,
"max_tokens_in_batch": 32768,
"block_size": 16,
"enable_prefix_caching": true,
"enable_chunked_prefill": true,
"long_prefill_token_threshold": 32768,
"trace_max_tokens": 32768,
"num_blocks_mode": "explicit",
"num_blocks": 15281,
"gpu_memory_utilization": 0.85,
"non_kv_cache_overhead_bytes": 0,
"decode_cuda_graph_mode": "none",
"enable_dummy_mode": false,
"linear_op_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/linear_op_full32k.csv",
"atten_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/attention_combined.csv",
"moe_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/moe_full32k.csv",
"prediction_max_prefill_chunk_size": 18000,
"prediction_max_batch_size": 128,
"prediction_max_tokens_per_request": 32768,
"skip_cpu_overhead_modeling": true,
"no_cache": true,
"dummy_execution_time_ms": 1.0
},
"configs": [
{
"id": "vllm_kv_15281_profile_full32k",
"description": "H20 TP1 Qwen3-30B-A3B with explicit vLLM TP1 KV blocks and H20 CUDA_EVENT profile timing; 200-request replay with timestamps scaled by 2 and 3."
}
]
}

61
configs/rs11_frontier_h20_tp2_profile_full32k_coder200_ts2_ts3.json Normal file
View File

@@ -0,0 +1,61 @@
{
"suite_id": "rs11_frontier_h20_tp2_profile_full32k_coder200_ts2_ts3",
"sim": "frontier_h20_tp2_profile_full32k",
"frontier": {
"root": "/tmp/replayserve-frontier-rs1b",
"mode": "patched_scratch",
"patches": [
"patches/frontier-vllm-v1-prefix-cache-chunked-prefill.patch",
"patches/frontier-vllm-0.11.1-profiling-compat.patch"
],
"profile_source": "dash1:/home/admin/cpfs/wjh/replayserve_frontier_profiles/h20_tp2_tp4_qwen3_30ba3b_full32k_20260625",
"profile_note": "Timing rows include H20 TP2 and TP4 for attention/MoE and TP1/TP2/TP4 for linear ops; TP2 runs use explicit TP2 vLLM KV capacity."
},
"fixtures": [
"coder_200_ts2",
"coder_200_ts3"
],
"defaults": {
"simulation_mode": "online",
"sys_arch": "co-location",
"cluster_scheduler": "sticky_round_robin",
"replica_scheduler": "vllm_v1",
"model_name": "qwen3-a3b-30b-moe",
"device": "h20",
"network_device": "h20_dgx",
"attn_tensor_parallel_size": 2,
"attn_data_parallel_size": 1,
"moe_tensor_parallel_size": 2,
"moe_expert_parallel_size": 1,
"num_pipeline_stages": 1,
"num_replicas": 1,
"batch_size_cap": 64,
"max_tokens_in_batch": 32768,
"block_size": 16,
"enable_prefix_caching": true,
"enable_chunked_prefill": true,
"long_prefill_token_threshold": 32768,
"trace_max_tokens": 32768,
"num_blocks_mode": "explicit",
"num_blocks": 69055,
"gpu_memory_utilization": 0.85,
"non_kv_cache_overhead_bytes": 0,
"decode_cuda_graph_mode": "none",
"enable_dummy_mode": false,
"linear_op_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/linear_op_tp2_tp4_full32k.csv",
"atten_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/attention_tp2_tp4_combined.csv",
"moe_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/moe_tp2_tp4_full32k.csv",
"prediction_max_prefill_chunk_size": 18000,
"prediction_max_batch_size": 128,
"prediction_max_tokens_per_request": 32768,
"skip_cpu_overhead_modeling": true,
"no_cache": true,
"dummy_execution_time_ms": 1.0
},
"configs": [
{
"id": "vllm_kv_69055_profile_full32k",
"description": "H20 TP2 Qwen3-30B-A3B with explicit vLLM TP2 KV blocks and H20 TP2 CUDA_EVENT profile timing."
}
]
}

74
configs/rs12_frontier_h20_tp2_tp4_profile_full32k_coder200_ts2_ts3.json Normal file
View File

@@ -0,0 +1,74 @@
{
"suite_id": "rs12_frontier_h20_tp2_tp4_profile_full32k_coder200_ts2_ts3",
"sim": "frontier_h20_tp2_tp4_profile_full32k",
"frontier": {
"root": "/tmp/replayserve-frontier-rs1b",
"mode": "patched_scratch",
"patches": [
"patches/frontier-vllm-v1-prefix-cache-chunked-prefill.patch",
"patches/frontier-vllm-0.11.1-profiling-compat.patch"
],
"profile_source": "dash1:/home/admin/cpfs/wjh/replayserve_frontier_profiles/h20_tp2_tp4_qwen3_30ba3b_full32k_20260625_true_mixed"
},
"fixtures": [
"coder_200_ts2",
"coder_200_ts3"
],
"defaults": {
"simulation_mode": "online",
"sys_arch": "co-location",
"cluster_scheduler": "sticky_round_robin",
"replica_scheduler": "vllm_v1",
"model_name": "qwen3-a3b-30b-moe",
"device": "h20",
"network_device": "h20_dgx",
"attn_tensor_parallel_size": 1,
"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": 64,
"max_tokens_in_batch": 32768,
"block_size": 16,
"enable_prefix_caching": true,
"enable_chunked_prefill": true,
"long_prefill_token_threshold": 32768,
"trace_max_tokens": 32768,
"num_blocks_mode": "explicit",
"num_blocks": 0,
"gpu_memory_utilization": 0.85,
"non_kv_cache_overhead_bytes": 0,
"decode_cuda_graph_mode": "none",
"enable_dummy_mode": false,
"linear_op_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/linear_op_tp2_tp4_full32k.csv",
"atten_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/attention_tp2_tp4_combined.csv",
"moe_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/moe_tp2_tp4_full32k.csv",
"prediction_max_prefill_chunk_size": 18000,
"prediction_max_batch_size": 128,
"prediction_max_tokens_per_request": 32768,
"skip_cpu_overhead_modeling": true,
"no_cache": false,
"dummy_execution_time_ms": 1.0
},
"configs": [
{
"id": "tp2_vllm_kv_69055_profile_full32k",
"description": "H20 TP2 Qwen3-30B-A3B with explicit vLLM TP2 KV blocks and H20 TP2 CUDA_EVENT profile timing.",
"overrides": {
"attn_tensor_parallel_size": 2,
"moe_tensor_parallel_size": 2,
"num_blocks": 69055
}
},
{
"id": "tp4_vllm_kv_177077_profile_full32k",
"description": "H20 TP4 Qwen3-30B-A3B with explicit vLLM TP4 KV blocks and H20 TP4 CUDA_EVENT profile timing.",
"overrides": {
"attn_tensor_parallel_size": 4,
"moe_tensor_parallel_size": 4,
"num_blocks": 177077
}
}
]
}

51
configs/rs3_tiny_sweep.json Normal file
View File

@@ -0,0 +1,51 @@
{
"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
}
}
]
}

53
configs/rs4_frontier_h20_tp1.json Normal file
View File

@@ -0,0 +1,53 @@
{
"suite_id": "rs4_frontier_h20_tp1",
"sim": "frontier_h20_tp1",
"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": "qwen3-a3b-30b-moe",
"device": "h20",
"network_device": "h20_dgx",
"attn_tensor_parallel_size": 1,
"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": 64,
"max_tokens_in_batch": 32768,
"block_size": 16,
"enable_prefix_caching": true,
"enable_chunked_prefill": true,
"long_prefill_token_threshold": 32768,
"trace_max_tokens": 32768,
"num_blocks_mode": "memory_planner",
"num_blocks": null,
"gpu_memory_utilization": 0.85,
"non_kv_cache_overhead_bytes": 0,
"dummy_execution_time_ms": 1.0
},
"configs": [
{
"id": "planner_kv",
"description": "H20 TP1 Qwen3-30B-A3B with Frontier memory planner KV capacity."
},
{
"id": "vllm_kv_15281",
"description": "H20 TP1 Qwen3-30B-A3B with explicit KV blocks matching real vLLM TP1 on dash2.",
"overrides": {
"num_blocks_mode": "explicit",
"num_blocks": 15281
}
}
]
}

59
configs/rs5_frontier_h20_tp1_profile.json Normal file
View File

@@ -0,0 +1,59 @@
{
"suite_id": "rs5_frontier_h20_tp1_profile",
"sim": "frontier_h20_tp1_profile",
"frontier": {
"root": "/tmp/replayserve-frontier-rs1b",
"mode": "patched_scratch",
"patches": [
"patches/frontier-vllm-v1-prefix-cache-chunked-prefill.patch",
"patches/frontier-vllm-0.11.1-profiling-compat.patch"
],
"profile_source": "dash2:/home/admin/cpfs/wjh/replayserve_frontier_profiles/h20_tp1_qwen3_30ba3b_20260624"
},
"fixtures": [
"coder_100"
],
"defaults": {
"simulation_mode": "online",
"sys_arch": "co-location",
"cluster_scheduler": "sticky_round_robin",
"replica_scheduler": "vllm_v1",
"model_name": "qwen3-a3b-30b-moe",
"device": "h20",
"network_device": "h20_dgx",
"attn_tensor_parallel_size": 1,
"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": 64,
"max_tokens_in_batch": 32768,
"block_size": 16,
"enable_prefix_caching": true,
"enable_chunked_prefill": true,
"long_prefill_token_threshold": 32768,
"trace_max_tokens": 32768,
"num_blocks_mode": "explicit",
"num_blocks": 15281,
"gpu_memory_utilization": 0.85,
"non_kv_cache_overhead_bytes": 0,
"decode_cuda_graph_mode": "none",
"enable_dummy_mode": false,
"linear_op_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/linear_op.csv",
"atten_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/attention_combined.csv",
"moe_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/moe_vllm_fused.csv",
"prediction_max_prefill_chunk_size": 18000,
"prediction_max_batch_size": 128,
"prediction_max_tokens_per_request": 32768,
"skip_cpu_overhead_modeling": true,
"no_cache": true,
"dummy_execution_time_ms": 1.0
},
"configs": [
{
"id": "vllm_kv_15281_profile",
"description": "H20 TP1 Qwen3-30B-A3B with explicit vLLM TP1 KV blocks and H20 CUDA_EVENT profile timing."
}
]
}

59
configs/rs6_frontier_h20_tp1_profile_full32k.json Normal file
View File

@@ -0,0 +1,59 @@
{
"suite_id": "rs6_frontier_h20_tp1_profile_full32k",
"sim": "frontier_h20_tp1_profile_full32k",
"frontier": {
"root": "/tmp/replayserve-frontier-rs1b",
"mode": "patched_scratch",
"patches": [
"patches/frontier-vllm-v1-prefix-cache-chunked-prefill.patch",
"patches/frontier-vllm-0.11.1-profiling-compat.patch"
],
"profile_source": "dash2:/home/admin/cpfs/wjh/replayserve_frontier_profiles/h20_tp1_qwen3_30ba3b_full32k_20260624"
},
"fixtures": [
"coder_100"
],
"defaults": {
"simulation_mode": "online",
"sys_arch": "co-location",
"cluster_scheduler": "sticky_round_robin",
"replica_scheduler": "vllm_v1",
"model_name": "qwen3-a3b-30b-moe",
"device": "h20",
"network_device": "h20_dgx",
"attn_tensor_parallel_size": 1,
"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": 64,
"max_tokens_in_batch": 32768,
"block_size": 16,
"enable_prefix_caching": true,
"enable_chunked_prefill": true,
"long_prefill_token_threshold": 32768,
"trace_max_tokens": 32768,
"num_blocks_mode": "explicit",
"num_blocks": 15281,
"gpu_memory_utilization": 0.85,
"non_kv_cache_overhead_bytes": 0,
"decode_cuda_graph_mode": "none",
"enable_dummy_mode": false,
"linear_op_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/linear_op_full32k.csv",
"atten_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/attention_combined.csv",
"moe_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/moe_full32k.csv",
"prediction_max_prefill_chunk_size": 18000,
"prediction_max_batch_size": 128,
"prediction_max_tokens_per_request": 32768,
"skip_cpu_overhead_modeling": true,
"no_cache": true,
"dummy_execution_time_ms": 1.0
},
"configs": [
{
"id": "vllm_kv_15281_profile_full32k",
"description": "H20 TP1 Qwen3-30B-A3B with explicit vLLM TP1 KV blocks and H20 CUDA_EVENT profile timing; linear and MoE coverage extended to 32768 tokens."
}
]
}

59
configs/rs8_frontier_h20_tp1_profile_full32k_coder500.json Normal file
View File

@@ -0,0 +1,59 @@
{
"suite_id": "rs8_frontier_h20_tp1_profile_full32k_coder500",
"sim": "frontier_h20_tp1_profile_full32k",
"frontier": {
"root": "/tmp/replayserve-frontier-rs1b",
"mode": "patched_scratch",
"patches": [
"patches/frontier-vllm-v1-prefix-cache-chunked-prefill.patch",
"patches/frontier-vllm-0.11.1-profiling-compat.patch"
],
"profile_source": "dash2:/home/admin/cpfs/wjh/replayserve_frontier_profiles/h20_tp1_qwen3_30ba3b_full32k_20260624"
},
"fixtures": [
"coder_500"
],
"defaults": {
"simulation_mode": "online",
"sys_arch": "co-location",
"cluster_scheduler": "sticky_round_robin",
"replica_scheduler": "vllm_v1",
"model_name": "qwen3-a3b-30b-moe",
"device": "h20",
"network_device": "h20_dgx",
"attn_tensor_parallel_size": 1,
"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": 64,
"max_tokens_in_batch": 32768,
"block_size": 16,
"enable_prefix_caching": true,
"enable_chunked_prefill": true,
"long_prefill_token_threshold": 32768,
"trace_max_tokens": 32768,
"num_blocks_mode": "explicit",
"num_blocks": 15281,
"gpu_memory_utilization": 0.85,
"non_kv_cache_overhead_bytes": 0,
"decode_cuda_graph_mode": "none",
"enable_dummy_mode": false,
"linear_op_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/linear_op_full32k.csv",
"atten_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/attention_combined.csv",
"moe_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/moe_full32k.csv",
"prediction_max_prefill_chunk_size": 18000,
"prediction_max_batch_size": 128,
"prediction_max_tokens_per_request": 32768,
"skip_cpu_overhead_modeling": true,
"no_cache": true,
"dummy_execution_time_ms": 1.0
},
"configs": [
{
"id": "vllm_kv_15281_profile_full32k",
"description": "H20 TP1 Qwen3-30B-A3B with explicit vLLM TP1 KV blocks and H20 CUDA_EVENT profile timing; 500-request replay stress."
}
]
}

59
configs/rs9_frontier_h20_tp1_profile_full32k_coder200_ts0667.json Normal file
View File

@@ -0,0 +1,59 @@
{
"suite_id": "rs9_frontier_h20_tp1_profile_full32k_coder200_ts0667",
"sim": "frontier_h20_tp1_profile_full32k",
"frontier": {
"root": "/tmp/replayserve-frontier-rs1b",
"mode": "patched_scratch",
"patches": [
"patches/frontier-vllm-v1-prefix-cache-chunked-prefill.patch",
"patches/frontier-vllm-0.11.1-profiling-compat.patch"
],
"profile_source": "dash2:/home/admin/cpfs/wjh/replayserve_frontier_profiles/h20_tp1_qwen3_30ba3b_full32k_20260624"
},
"fixtures": [
"coder_200_ts0667"
],
"defaults": {
"simulation_mode": "online",
"sys_arch": "co-location",
"cluster_scheduler": "sticky_round_robin",
"replica_scheduler": "vllm_v1",
"model_name": "qwen3-a3b-30b-moe",
"device": "h20",
"network_device": "h20_dgx",
"attn_tensor_parallel_size": 1,
"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": 64,
"max_tokens_in_batch": 32768,
"block_size": 16,
"enable_prefix_caching": true,
"enable_chunked_prefill": true,
"long_prefill_token_threshold": 32768,
"trace_max_tokens": 32768,
"num_blocks_mode": "explicit",
"num_blocks": 15281,
"gpu_memory_utilization": 0.85,
"non_kv_cache_overhead_bytes": 0,
"decode_cuda_graph_mode": "none",
"enable_dummy_mode": false,
"linear_op_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/linear_op_full32k.csv",
"atten_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/attention_combined.csv",
"moe_input_file": "./data/profiling/compute/h20/qwen3-a3b-30b-moe/moe_full32k.csv",
"prediction_max_prefill_chunk_size": 18000,
"prediction_max_batch_size": 128,
"prediction_max_tokens_per_request": 32768,
"skip_cpu_overhead_modeling": true,
"no_cache": true,
"dummy_execution_time_ms": 1.0
},
"configs": [
{
"id": "vllm_kv_15281_profile_full32k",
"description": "H20 TP1 Qwen3-30B-A3B with explicit vLLM TP1 KV blocks and H20 CUDA_EVENT profile timing; 200-request replay with timestamps scaled by 2/3."
}
]
}