Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
107 lines
3.1 KiB
JSON
107 lines
3.1 KiB
JSON
[
|
|
{
|
|
"test_name": "latency_llama8B_tp1",
|
|
"environment_variables": {
|
|
"PT_HPU_LAZY_MODE": 1,
|
|
"VLLM_CONTIGUOUS_PA": 1,
|
|
"VLLM_DEFRAG": 1
|
|
},
|
|
"parameters": {
|
|
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
|
"tensor_parallel_size": 1,
|
|
"load_format": "dummy",
|
|
"num-iters-warmup": 5,
|
|
"num-iters": 15,
|
|
"max-model-len": 256,
|
|
"async-scheduling": ""
|
|
}
|
|
},
|
|
{
|
|
"test_name": "latency_llama70B_tp4",
|
|
"environment_variables": {
|
|
"PT_HPU_LAZY_MODE": 1,
|
|
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
|
"VLLM_CONTIGUOUS_PA": 1,
|
|
"VLLM_DEFRAG": 1
|
|
},
|
|
"parameters": {
|
|
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
|
"tensor_parallel_size": 4,
|
|
"load_format": "dummy",
|
|
"num-iters-warmup": 5,
|
|
"num-iters": 15,
|
|
"max-model-len": 256,
|
|
"async-scheduling": ""
|
|
}
|
|
},
|
|
{
|
|
"test_name": "latency_mixtral8x7B_tp2",
|
|
"environment_variables": {
|
|
"PT_HPU_LAZY_MODE": 1,
|
|
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
|
"VLLM_CONTIGUOUS_PA": 1,
|
|
"VLLM_DEFRAG": 1
|
|
},
|
|
"parameters": {
|
|
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
|
"tensor_parallel_size": 2,
|
|
"load_format": "dummy",
|
|
"num-iters-warmup": 5,
|
|
"num-iters": 15,
|
|
"max-model-len": 256,
|
|
"async-scheduling": ""
|
|
}
|
|
},
|
|
{
|
|
"test_name": "latency_deepseek_r1",
|
|
"environment_variables": {
|
|
"PT_HPU_LAZY_MODE": 1,
|
|
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
|
"VLLM_CONTIGUOUS_PA": 1,
|
|
"VLLM_DEFRAG": 1
|
|
},
|
|
"parameters": {
|
|
"model": "deepseek-ai/DeepSeek-R1",
|
|
"tensor_parallel_size": 8,
|
|
"load_format": "dummy",
|
|
"max-model-len": 2048,
|
|
"dtype": "bfloat16"
|
|
}
|
|
},
|
|
{
|
|
"test_name": "latency_llama4_maverick_17b128e_instruct_fp8",
|
|
"environment_variables": {
|
|
"PT_HPU_LAZY_MODE": 1,
|
|
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
|
"VLLM_CONTIGUOUS_PA": 1,
|
|
"VLLM_DEFRAG": 1
|
|
},
|
|
"parameters": {
|
|
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
|
|
"tensor_parallel_size": 8,
|
|
"max-model-len": 512,
|
|
"max-num-seqs": 128,
|
|
"async-scheduling": "",
|
|
"gpu-memory-utilization": 0.95,
|
|
"enable_expert_parallel": ""
|
|
}
|
|
},
|
|
{
|
|
"test_name": "latency_qwen3_8b",
|
|
"environment_variables": {
|
|
"PT_HPU_LAZY_MODE": 1,
|
|
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
|
"VLLM_CONTIGUOUS_PA": 1,
|
|
"VLLM_DEFRAG": 1
|
|
},
|
|
"parameters": {
|
|
"model": "Qwen/Qwen3-8B",
|
|
"tensor_parallel_size": 1,
|
|
"max-model-len": 2048,
|
|
"max-num-seqs": 128,
|
|
"dtype": "bfloat16",
|
|
"async-scheduling": ""
|
|
}
|
|
}
|
|
]
|