gahow/agentic-kvc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add vLLM v0.18.1 source tree with KV transfer abort fix

Browse Source 
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>
This commit is contained in:
Gahow Wang
2026-05-22 00:30:38 +08:00
parent b6591950bc
commit 445e491123
4285 changed files with 1111303 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
third_party/vllm/.buildkite/performance-benchmarks/tests/genai-perf-tests.json vendored Normal file
View File

@@ -0,0 +1,21 @@
[
{
"test_name": "llama8B_tp1_genai_perf",
"qps_list": [4,8,16,32],
"common_parameters": {
"model": "meta-llama/Meta-Llama-3-8B-Instruct",
"tp": 1,
"port": 8000,
"num_prompts": 500,
"reuse_server": false
},
"vllm_server_parameters": {
"disable_log_stats": "",
"gpu_memory_utilization": 0.9,
"max_num_seqs": 512,
"dtype": "bfloat16"
},
"genai_perf_input_parameters": {
}
}
]

26
third_party/vllm/.buildkite/performance-benchmarks/tests/latency-tests-arm64-cpu.json vendored Normal file
View File

@@ -0,0 +1,26 @@
[
{
"test_name": "latency_llama8B_tp1",
"environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"load_format": "dummy",
"dtype": "bfloat16",
"distributed_executor_backend": "mp",
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
"num_iters_warmup": 5,
"num_iters": 15
}
}
]

26
third_party/vllm/.buildkite/performance-benchmarks/tests/latency-tests-cpu.json vendored Normal file
View File

@@ -0,0 +1,26 @@
[
{
"test_name": "latency_llama8B_tp2",
"environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_SGL_KERNEL": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"tensor_parallel_size": 2,
"dtype": "bfloat16",
"distributed_executor_backend": "mp",
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
"num_iters_warmup": 5,
"num_iters": 15
}
}
]

106
third_party/vllm/.buildkite/performance-benchmarks/tests/latency-tests-hpu.json vendored Normal file
View File

@@ -0,0 +1,106 @@
[
{
"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": ""
}
}
]

32
third_party/vllm/.buildkite/performance-benchmarks/tests/latency-tests.json vendored Normal file
View File

@@ -0,0 +1,32 @@
[
{
"test_name": "latency_llama8B_tp1",
"parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"load_format": "dummy",
"num_iters_warmup": 5,
"num_iters": 15
}
},
{
"test_name": "latency_llama70B_tp4",
"parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tensor_parallel_size": 4,
"load_format": "dummy",
"num-iters-warmup": 5,
"num-iters": 15
}
},
{
"test_name": "latency_mixtral8x7B_tp2",
"parameters": {
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"tensor_parallel_size": 2,
"load_format": "dummy",
"num-iters-warmup": 5,
"num-iters": 15
}
}
]

311
third_party/vllm/.buildkite/performance-benchmarks/tests/nightly-tests.json vendored Normal file
View File

@@ -0,0 +1,311 @@
[
{
"test_name": "llama8B_tp1_sharegpt",
"qps_list": [4,8,16,32,"inf"],
"common_parameters": {
"model": "meta-llama/Meta-Llama-3-8B-Instruct",
"tp": 1,
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 500,
"port": 8000,
"reuse_server": false
},
"lmdeploy_server_parameters": {
"dtype": "bfloat16"
},
"lmdeploy_client_parameters": {
},
"tgi_server_parameters": {
},
"tgi_client_parameters": {
"endpoint": "/generate_stream"
},
"trt_server_parameters": {
"model_type": "llama",
"model_dtype": "bfloat16",
"max_batch_size": 2048,
"max_input_len": 4096,
"max_seq_len": 6144,
"max_num_tokens": 16384,
"trt_llm_version": "v0.11.0"
},
"trt_client_parameters": {
"endpoint": "/v2/models/ensemble/generate_stream"
},
"vllm_server_parameters": {
"disable_log_stats": "",
"gpu_memory_utilization": 0.9,
"max_num_seqs": 512,
"dtype": "bfloat16"
},
"vllm_client_parameters": {
},
"sglang_server_parameters": {
"disable_radix_cache": "",
"enable_torch_compile": "",
"dtype": "bfloat16"
},
"sglang_client_parameters": {
}
},
{
"test_name": "llama8B_tp1_sonnet_512_16",
"qps_list": [4,8,16,32,"inf"],
"common_parameters": {
"model": "meta-llama/Meta-Llama-3-8B-Instruct",
"tp": 1,
"dataset_name": "sonnet",
"dataset_path": "./sonnet_4x.txt",
"num_prompts": 500,
"port": 8000,
"sonnet_input_len": 512,
"sonnet_output_len": 16,
"sonnet_prefix_len": 50,
"reuse_server": true
},
"lmdeploy_server_parameters": {
"dtype": "bfloat16"
},
"lmdeploy_client_parameters": {
},
"tgi_server_parameters": {
},
"tgi_client_parameters": {
"endpoint": "/generate_stream"
},
"trt_server_parameters": {
"model_type": "llama",
"model_dtype": "bfloat16",
"max_batch_size": 2048,
"max_input_len": 4096,
"max_seq_len": 6144,
"max_num_tokens": 16384,
"trt_llm_version": "v0.11.0"
},
"trt_client_parameters": {
"endpoint": "/v2/models/ensemble/generate_stream"
},
"vllm_server_parameters": {
"disable_log_stats": "",
"gpu_memory_utilization": 0.9,
"max_num_seqs": 512,
"dtype": "bfloat16"
},
"vllm_client_parameters": {
},
"sglang_server_parameters": {
"disable_radix_cache": "",
"enable_torch_compile": "",
"dtype": "bfloat16"
},
"sglang_client_parameters": {
}
},
{
"test_name": "llama8B_tp1_sonnet_512_256",
"qps_list": [4,8,16,32,"inf"],
"common_parameters": {
"model": "meta-llama/Meta-Llama-3-8B-Instruct",
"tp": 1,
"dataset_name": "sonnet",
"dataset_path": "./sonnet_4x.txt",
"num_prompts": 500,
"port": 8000,
"sonnet_input_len": 512,
"sonnet_output_len": 256,
"sonnet_prefix_len": 50,
"reuse_server": true
},
"lmdeploy_server_parameters": {
"dtype": "bfloat16"
},
"lmdeploy_client_parameters": {
},
"tgi_server_parameters": {
},
"tgi_client_parameters": {
"endpoint": "/generate_stream"
},
"trt_server_parameters": {
"model_type": "llama",
"model_dtype": "bfloat16",
"max_batch_size": 2048,
"max_input_len": 4096,
"max_seq_len": 6144,
"max_num_tokens": 16384,
"trt_llm_version": "v0.11.0"
},
"trt_client_parameters": {
"endpoint": "/v2/models/ensemble/generate_stream"
},
"vllm_server_parameters": {
"disable_log_stats": "",
"gpu_memory_utilization": 0.9,
"max_num_seqs": 512,
"dtype": "bfloat16"
},
"vllm_client_parameters": {
},
"sglang_server_parameters": {
"disable_radix_cache": "",
"enable_torch_compile": "",
"dtype": "bfloat16"
},
"sglang_client_parameters": {
}
},
{
"test_name": "llama70B_tp4_sharegpt",
"qps_list": [4,8,16,32,"inf"],
"common_parameters": {
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
"tp": 4,
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 500,
"port": 8000,
"reuse_server": false
},
"lmdeploy_server_parameters": {
"dtype": "bfloat16"
},
"lmdeploy_client_parameters": {
},
"tgi_server_parameters": {
},
"tgi_client_parameters": {
"endpoint": "/generate_stream"
},
"trt_server_parameters": {
"model_type": "llama",
"model_dtype": "bfloat16",
"max_batch_size": 2048,
"max_input_len": 4096,
"max_seq_len": 6144,
"max_num_tokens": 16384,
"trt_llm_version": "v0.11.0"
},
"trt_client_parameters": {
"endpoint": "/v2/models/ensemble/generate_stream"
},
"vllm_server_parameters": {
"disable_log_stats": "",
"gpu_memory_utilization": 0.9,
"max_num_seqs": 512,
"dtype": "bfloat16"
},
"vllm_client_parameters": {
},
"sglang_server_parameters": {
"disable_radix_cache": "",
"dtype": "bfloat16"
},
"sglang_client_parameters": {
}
},
{
"test_name": "llama70B_tp4_sonnet_512_16",
"qps_list": [4,8,16,32,"inf"],
"common_parameters": {
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
"tp": 4,
"dataset_name": "sonnet",
"dataset_path": "./sonnet_4x.txt",
"num_prompts": 500,
"port": 8000,
"sonnet_input_len": 512,
"sonnet_output_len": 16,
"sonnet_prefix_len": 50,
"reuse_server": true
},
"lmdeploy_server_parameters": {
"dtype": "bfloat16"
},
"lmdeploy_client_parameters": {
},
"tgi_server_parameters": {
},
"tgi_client_parameters": {
"endpoint": "/generate_stream"
},
"trt_server_parameters": {
"model_type": "llama",
"model_dtype": "bfloat16",
"max_batch_size": 2048,
"max_input_len": 4096,
"max_seq_len": 6144,
"max_num_tokens": 16384,
"trt_llm_version": "v0.11.0"
},
"trt_client_parameters": {
"endpoint": "/v2/models/ensemble/generate_stream"
},
"vllm_server_parameters": {
"disable_log_stats": "",
"gpu_memory_utilization": 0.9,
"max_num_seqs": 512,
"dtype": "bfloat16"
},
"vllm_client_parameters": {
},
"sglang_server_parameters": {
"disable_radix_cache": "",
"dtype": "bfloat16"
},
"sglang_client_parameters": {
}
},
{
"test_name": "llama70B_tp4_sonnet_512_256",
"qps_list": [4,8,16,32,"inf"],
"common_parameters": {
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
"tp": 4,
"dataset_name": "sonnet",
"dataset_path": "./sonnet_4x.txt",
"num_prompts": 500,
"port": 8000,
"sonnet_input_len": 512,
"sonnet_output_len": 256,
"sonnet_prefix_len": 50,
"reuse_server": true
},
"lmdeploy_server_parameters": {
"dtype": "bfloat16"
},
"lmdeploy_client_parameters": {
},
"tgi_server_parameters": {
},
"tgi_client_parameters": {
"endpoint": "/generate_stream"
},
"trt_server_parameters": {
"model_type": "llama",
"model_dtype": "bfloat16",
"max_batch_size": 2048,
"max_input_len": 4096,
"max_seq_len": 6144,
"max_num_tokens": 16384,
"trt_llm_version": "v0.11.0"
},
"trt_client_parameters": {
"endpoint": "/v2/models/ensemble/generate_stream"
},
"vllm_server_parameters": {
"disable_log_stats": "",
"gpu_memory_utilization": 0.9,
"max_num_seqs": 512,
"dtype": "bfloat16"
},
"vllm_client_parameters": {
},
"sglang_server_parameters": {
"disable_radix_cache": "",
"dtype": "bfloat16"
},
"sglang_client_parameters": {
}
}
]

130
third_party/vllm/.buildkite/performance-benchmarks/tests/serving-tests-arm64-cpu.json vendored Normal file
View File

@@ -0,0 +1,130 @@
{
"defaults": {
"qps_list": [
"inf"
],
"max_concurrency_list": [
12,
16,
24,
32,
64,
128,
200
],
"server_environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_SGL_KERNEL": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"dtype": "bfloat16",
"distributed_executor_backend": "mp",
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
"load_format": "dummy"
},
"client_parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"backend": "vllm",
"ignore-eos": "",
"num_prompts": 200
}
},
"tests": [
{
"test_name": "serving_llama8B_tp1_sharegpt",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
}
},
{
"test_name": "serving_llama8B_tp2_sharegpt",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
}
},
{
"test_name": "serving_llama8B_tp1_random_128_128",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp2_random_128_128",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp1_random_128_2048",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp2_random_128_2048",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp1_random_2048_128",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp2_random_2048_128",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 128
}
}
]
}

37
third_party/vllm/.buildkite/performance-benchmarks/tests/serving-tests-cpu-asr.json vendored Normal file
View File

@@ -0,0 +1,37 @@
{
"defaults": {
"qps_list": [
"inf"
],
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
"server_environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120
},
"server_parameters": {
"dtype": "bfloat16",
"model": "openai/whisper-large-v3-turbo"
},
"client_parameters": {
"model": "openai/whisper-large-v3-turbo",
"backend": "openai-audio",
"endpoint": "/v1/audio/transcriptions",
"dataset_name": "hf",
"dataset_path": "openslr/librispeech_asr",
"hf_subset": "clean",
"hf_split": "test",
"no_stream": "",
"no_oversample": "",
"num_prompts": 200
}
},
"tests": [
{
"test_name": "serving_whisper_large_v3_turbo_librispeech_clean_tp1",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {}
}
]
}

41
third_party/vllm/.buildkite/performance-benchmarks/tests/serving-tests-cpu-embed.json vendored Normal file
View File

@@ -0,0 +1,41 @@
{
"defaults": {
"qps_list": [
"inf"
],
"max_concurrency_list": [
32,
64,
128
],
"server_environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_SGL_KERNEL": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
"dtype": "bfloat16",
"model": "jinaai/jina-embeddings-v3",
"trust_remote_code": ""
},
"client_parameters": {
"model": "jinaai/jina-embeddings-v3",
"backend": "openai-embeddings",
"endpoint": "/v1/embeddings",
"dataset_name": "sharegpt",
"dataset_path": "ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
},
"tests": [
{
"test_name": "serving_jina_embed_v3_tp1_sharegpt",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {}
}
]
}

355
third_party/vllm/.buildkite/performance-benchmarks/tests/serving-tests-cpu-text.json vendored Normal file
View File

@@ -0,0 +1,355 @@
{
"defaults": {
"qps_list": [
"inf"
],
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
"server_environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_SGL_KERNEL": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"dtype": "bfloat16",
"distributed_executor_backend": "mp",
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256
},
"client_parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"backend": "vllm",
"ignore-eos": "",
"num_prompts": 200
}
},
"tests": [
{
"test_name": "serving_llama8B_tp1_sharegpt",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
}
},
{
"test_name": "serving_llama8B_tp2_sharegpt",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
}
},
{
"test_name": "serving_llama8B_tp1_random_128_128",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp2_random_128_128",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp4_random_128_128",
"server_parameters": {
"tensor_parallel_size": 4
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp1_random_128_2048",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp2_random_128_2048",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp4_random_128_2048",
"server_parameters": {
"tensor_parallel_size": 4
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp1_random_2048_128",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp2_random_2048_128",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp4_random_2048_128",
"server_parameters": {
"tensor_parallel_size": 4
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp1_random_2048_2048",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp2_random_2048_2048",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp4_random_2048_2048",
"server_parameters": {
"tensor_parallel_size": 4
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_int4_tp1_random_128_128",
"server_parameters": {
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_int4_tp2_random_128_128",
"server_parameters": {
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
"tensor_parallel_size": 2
},
"client_parameters": {
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_int4_tp4_random_128_128",
"server_parameters": {
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
"tensor_parallel_size": 4
},
"client_parameters": {
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_int8_tp1_random_128_128",
"server_parameters": {
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_int8_tp2_random_128_128",
"server_parameters": {
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",
"tensor_parallel_size": 2
},
"client_parameters": {
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_int8_tp4_random_128_128",
"server_parameters": {
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",
"tensor_parallel_size": 4
},
"client_parameters": {
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama3B_tp1_random_128_128",
"server_parameters": {
"model": "meta-llama/Llama-3.2-3B-Instruct",
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "meta-llama/Llama-3.2-3B-Instruct",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_granite2B_tp1_random_128_128",
"server_parameters": {
"model": "ibm-granite/granite-3.2-2b-instruct",
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "ibm-granite/granite-3.2-2b-instruct",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_qwen1.7B_tp1_random_128_128",
"server_parameters": {
"model": "Qwen/Qwen3-1.7B",
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "Qwen/Qwen3-1.7B",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_qwen4B_tp1_random_128_128",
"server_parameters": {
"model": "Qwen/Qwen3-4B",
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "Qwen/Qwen3-4B",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_qwen8B_tp1_random_128_128",
"server_parameters": {
"model": "Qwen/Qwen3-8B",
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "Qwen/Qwen3-8B",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_glm9B_tp1_random_128_128",
"server_parameters": {
"model": "zai-org/glm-4-9b-hf",
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "zai-org/glm-4-9b-hf",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_gemma7B_tp1_random_128_128",
"server_parameters": {
"model": "google/gemma-7b",
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "google/gemma-7b",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
}
]
}

142
third_party/vllm/.buildkite/performance-benchmarks/tests/serving-tests-cpu.json vendored Normal file
View File

@@ -0,0 +1,142 @@
{
"defaults": {
"qps_list": [
"inf"
],
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
"server_environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_SGL_KERNEL": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"dtype": "bfloat16",
"distributed_executor_backend": "mp",
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256
},
"client_parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"backend": "vllm",
"ignore-eos": "",
"num_prompts": 200
}
},
"tests": [
{
"test_name": "serving_llama8B_tp1_sharegpt",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
}
},
{
"test_name": "serving_llama8B_tp2_sharegpt",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
}
},
{
"test_name": "serving_llama8B_tp1_random_128_128",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp2_random_128_128",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp1_random_128_2048",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp2_random_128_2048",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp1_random_2048_128",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp2_random_2048_128",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp1_random_2048_2048",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp2_random_2048_2048",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 2048
}
}
]
}

157
third_party/vllm/.buildkite/performance-benchmarks/tests/serving-tests-hpu.json vendored Normal file
View File

@@ -0,0 +1,157 @@
[
{
"test_name": "serving_llama8B_tp1_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"server_environment_variables": {
"PT_HPU_LAZY_MODE": 1,
"VLLM_CONTIGUOUS_PA": 1,
"VLLM_DEFRAG": 1
},
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"disable_log_stats": "",
"load_format": "dummy",
"max-model-len": 2048,
"max-num-seqs": 256,
"async-scheduling": ""
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
},
{
"test_name": "serving_llama70B_tp4_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"server_environment_variables": {
"PT_HPU_LAZY_MODE": 1,
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
"VLLM_CONTIGUOUS_PA": 1,
"VLLM_DEFRAG": 1
},
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tensor_parallel_size": 4,
"disable_log_stats": "",
"load_format": "dummy",
"max-model-len": 2048,
"max-num-seqs": 256,
"async-scheduling": ""
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
},
{
"test_name": "serving_mixtral8x7B_tp2_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"server_environment_variables": {
"PT_HPU_LAZY_MODE": 1,
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
"VLLM_CONTIGUOUS_PA": 1,
"VLLM_DEFRAG": 1
},
"server_parameters": {
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"tensor_parallel_size": 2,
"disable_log_stats": "",
"load_format": "dummy",
"max-model-len": 2048,
"max-num-seqs": 256,
"async-scheduling": ""
},
"client_parameters": {
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
},
{
"test_name": "serving_deepseek_r1",
"qps_list": [1, 4, 16, "inf"],
"server_environment_variables": {
"PT_HPU_LAZY_MODE": 1,
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
"VLLM_CONTIGUOUS_PA": 1,
"VLLM_DEFRAG": 1
},
"server_parameters": {
"model": "deepseek-ai/DeepSeek-R1",
"tensor_parallel_size": 8,
"disable_log_stats": "",
"load_format": "dummy",
"max-model-len": 2048,
"max-num-seqs": 200,
"async-scheduling": "",
"dtype": "bfloat16"
},
"client_parameters": {
"model": "deepseek-ai/DeepSeek-R1",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
},
{
"test_name": "serving_llama4_maverick_17b128e_instruct_fp8",
"qps_list": [1, 4, 16, "inf"],
"server_environment_variables": {
"PT_HPU_LAZY_MODE": 1,
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
"VLLM_CONTIGUOUS_PA": 1,
"VLLM_DEFRAG": 1
},
"server_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"tensor_parallel_size": 8,
"disable_log_stats": "",
"max-model-len": 2048,
"max-num-seqs": 128,
"async-scheduling": "",
"enable_expert_parallel": "",
"max-num-batched-tokens": 4096
},
"client_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
},
{
"test_name": "serving_qwen3_8b",
"qps_list": [1, 4, 10, "inf"],
"server_environment_variables": {
"PT_HPU_LAZY_MODE": 1,
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
"VLLM_CONTIGUOUS_PA": 1,
"VLLM_DEFRAG": 1
},
"server_parameters": {
"model": "Qwen/Qwen-3-8B",
"tensor_parallel_size": 1,
"dtype": "bfloat16",
"disable_log_stats": "",
"async-scheduling": ""
},
"client_parameters": {
"model": "Qwen/Qwen-3-8B",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
}
]

73
third_party/vllm/.buildkite/performance-benchmarks/tests/serving-tests.json vendored Normal file
View File

@@ -0,0 +1,73 @@
[
{
"test_name": "serving_llama8B_tp1_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"disable_log_stats": "",
"load_format": "dummy"
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
},
{
"test_name": "serving_llama70B_tp4_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tensor_parallel_size": 4,
"disable_log_stats": "",
"load_format": "dummy"
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
},
{
"test_name": "serving_mixtral8x7B_tp2_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"server_parameters": {
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"tensor_parallel_size": 2,
"disable_log_stats": "",
"load_format": "dummy"
},
"client_parameters": {
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
},
{
"test_name": "serving_llama70B_tp4_sharegpt_specdecode",
"qps_list": [2],
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tensor_parallel_size": 4,
"speculative_config": {
"model": "turboderp/Qwama-0.5B-Instruct",
"num_speculative_tokens": 4,
"draft_tensor_parallel_size": 1
}
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
}
]

27
third_party/vllm/.buildkite/performance-benchmarks/tests/throughput-tests-arm64-cpu.json vendored Normal file
View File

@@ -0,0 +1,27 @@
[
{
"test_name": "throughput_llama8B_tp1",
"environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"load_format": "dummy",
"dtype": "bfloat16",
"distributed_executor_backend": "mp",
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200,
"backend": "vllm"
}
}
]

27
third_party/vllm/.buildkite/performance-benchmarks/tests/throughput-tests-cpu.json vendored Normal file
View File

@@ -0,0 +1,27 @@
[
{
"test_name": "throughput_llama8B_tp2",
"environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_SGL_KERNEL": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"tensor_parallel_size": 2,
"dtype": "bfloat16",
"distributed_executor_backend": "mp",
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200,
"backend": "vllm"
}
}
]

123
third_party/vllm/.buildkite/performance-benchmarks/tests/throughput-tests-hpu.json vendored Normal file
View File

@@ -0,0 +1,123 @@
[
{
"test_name": "throughput_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",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 1000,
"backend": "vllm",
"max-model-len": 2048,
"max-num-seqs": 512,
"async-scheduling": ""
}
},
{
"test_name": "throughput_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",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 1000,
"backend": "vllm",
"max-model-len": 2048,
"max-num-seqs": 512,
"async-scheduling": ""
}
},
{
"test_name": "throughput_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",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 1000,
"backend": "vllm",
"max-model-len": 2048,
"max-num-seqs": 512,
"async-scheduling": ""
}
},
{
"test_name": "throughput_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",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"dataset_name": "sharegpt",
"num_prompts": 1000,
"backend": "vllm",
"max-model-len": 2048,
"max-num-seqs": 384,
"async-scheduling": ""
}
},
{
"test_name": "throughput_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,
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"dataset_name": "sharegpt",
"num_prompts": 1000,
"backend": "vllm",
"max-model-len": 2048,
"max-num-seqs": 512,
"async-scheduling": "",
"enable_expert_parallel": ""
}
},
{
"test_name": "throughput_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/Qwen-3-8B",
"tensor_parallel_size": 1,
"load_format": "dummy",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"dataset_name": "sharegpt",
"num_prompts": 1000,
"max-num-seqs": 512,
"backend": "vllm",
"async-scheduling": ""
}
}
]

35
third_party/vllm/.buildkite/performance-benchmarks/tests/throughput-tests.json vendored Normal file
View File

@@ -0,0 +1,35 @@
[
{
"test_name": "throughput_llama8B_tp1",
"parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"load_format": "dummy",
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200,
"backend": "vllm"
}
},
{
"test_name": "throughput_llama70B_tp4",
"parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tensor_parallel_size": 4,
"load_format": "dummy",
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200,
"backend": "vllm"
}
},
{
"test_name": "throughput_mixtral8x7B_tp2",
"parameters": {
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"tensor_parallel_size": 2,
"load_format": "dummy",
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200,
"backend": "vllm"
}
}
]