Freeze code long context profile v6

This commit is contained in:
2026-07-24 00:52:23 +08:00
parent 89d5ebbbc0
commit b80d3f03de
60 changed files with 5353 additions and 1 deletions

View File

@@ -0,0 +1,8 @@
6ee8fdf15bef211e7d53fef0c5daf02b17429bc7d88a49cb967c2b2f6134ebe2 runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/raw/flashattn-code-longctx-tp4.json
4e6d6002db037bdc71d40f76d6de979ef47960612c15dd985c04048c25bd1d41 runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/aituner.commit
420e4a613b1bcdb44b873eaa911f4a23129713ff9d486fc783b31a009a55cc85 runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/batch-specs.txt
5dd612a7806900e9d12afc27ccef196cc5518aea831aa4ed3b0a53bcfb5746cf runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/max-model-len.txt
484da176e7355ab5532d5129a8e78bea0ae84b3aa0a42c7f0bea9689667762ff runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/pip-freeze.txt
595b25965f76bf7ac25aa3b60126a437a083619303303aaf63346e993862253a runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/source.sha256
4355a46b19d348dc2f57c046f8ef63d4538ebb936000f3c9ee954a27460dd865 runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/vllm-allow-long-max-model-len.txt
11e8f5af440e3db4c01b519a7b0e30bbcecc3a57bfb53dd86d32e601beb95a32 runs/frontier-code-trace-v0/profiles/raw/tp4-r2-v2/provenance/vllm-source.commit

View File

@@ -0,0 +1 @@
e251046c306a8e03214fe1b2f40caabb98f76b7b

View File

@@ -0,0 +1,13 @@
q8ks48k
q8ks64k
q8ks80k
q8ks96k
q8ks112k
q8ks128k
q8ks136k
q512s128k
q2ks66k
q4ks100k
q6ks134k
q1ks8k
q512s4k

View File

@@ -0,0 +1,179 @@
aiohappyeyeballs==2.7.1
aiohttp==3.14.1
aiosignal==1.4.0
annotated-doc==0.0.4
annotated-types==0.7.0
anthropic==0.117.0
anyio==4.14.2
apache-tvm-ffi==0.1.9
astor==0.8.1
attrs==26.1.0
blake3==1.0.9
cachetools==7.1.4
cbor2==6.1.3
certifi==2026.6.17
cffi==2.1.0
charset-normalizer==3.4.9
click==8.4.2
cloudpickle==3.1.2
compressed-tensors==0.15.0.1
cryptography==49.0.0
cuda-bindings==12.9.7
cuda-pathfinder==1.5.6
cuda-python==12.9.7
cuda-tile==1.5.0
cuda-toolkit==12.9.1
depyf==0.20.0
detect-installer==0.1.0
dill==0.4.1
diskcache==5.6.3
distro==1.9.0
dnspython==2.8.0
docstring-parser==0.18.0
einops==0.8.2
email-validator==2.3.0
fastapi==0.139.2
fastapi-cli==0.0.32
fastapi-cloud-cli==0.22.2
fastar==0.11.0
fastsafetensors==0.3.3
filelock==3.31.1
flashinfer-cubin==0.6.8.post1
flashinfer-python==0.6.8.post1
frozenlist==1.8.0
fsspec==2026.6.0
gguf==0.19.0
googleapis-common-protos==1.75.0
grpcio==1.82.1
h11==0.16.0
hf-xet==1.5.2
httpcore==1.0.9
httptools==0.8.0
httpx==0.28.1
httpx-sse==0.4.3
huggingface-hub==1.24.0
idna==3.18
ijson==3.5.1
interegular==0.3.3
jinja2==3.1.6
jiter==0.16.0
jmespath==1.1.0
jsonschema==4.26.0
jsonschema-specifications==2025.9.1
lark==1.2.2
llguidance==1.3.0
llvmlite==0.47.0
lm-format-enforcer==0.11.3
loguru==0.7.3
markdown-it-py==4.2.0
markupsafe==3.0.3
mcp==1.28.1
mdurl==0.1.2
mistral-common==1.11.6
ml-dtypes==0.5.4
model-hosting-container-standards==0.1.16
mpmath==1.3.0
msgspec==0.21.1
multidict==6.7.1
networkx==3.6.1
ninja==1.13.0
numba==0.65.0
numpy==2.3.5
nvidia-cublas-cu12==12.9.1.4
nvidia-cuda-cupti-cu12==12.9.79
nvidia-cuda-nvrtc-cu12==12.9.86
nvidia-cuda-runtime-cu12==12.9.79
nvidia-cudnn-cu12==9.17.1.4
nvidia-cudnn-frontend==1.18.0
nvidia-cufft-cu12==11.4.1.4
nvidia-cufile-cu12==1.14.1.1
nvidia-curand-cu12==10.3.10.19
nvidia-cusolver-cu12==11.7.5.82
nvidia-cusparse-cu12==12.5.10.65
nvidia-cusparselt-cu12==0.7.1
nvidia-cutlass-dsl==4.5.3
nvidia-cutlass-dsl-libs-base==4.5.3
nvidia-ml-py==13.610.43
nvidia-nccl-cu12==2.28.9
nvidia-nvjitlink-cu12==12.9.86
nvidia-nvshmem-cu12==3.4.5
nvidia-nvtx-cu12==12.9.79
openai==2.46.0
openai-harmony==0.0.8
opencv-python-headless==5.0.0.93
opentelemetry-api==1.44.0
opentelemetry-exporter-otlp==1.44.0
opentelemetry-exporter-otlp-proto-common==1.44.0
opentelemetry-exporter-otlp-proto-grpc==1.44.0
opentelemetry-exporter-otlp-proto-http==1.44.0
opentelemetry-proto==1.44.0
opentelemetry-sdk==1.44.0
opentelemetry-semantic-conventions==0.65b0
opentelemetry-semantic-conventions-ai==0.5.1
outlines-core==0.2.14
packaging==26.2
partial-json-parser==0.2.1.1.post7
pillow==12.3.0
prometheus-client==0.25.0
prometheus-fastapi-instrumentator==8.0.2
propcache==0.5.2
protobuf==7.35.1
psutil==7.2.2
py-cpuinfo==9.0.0
pybase64==1.4.3
pycountry==26.2.16
pycparser==3.0
pydantic==2.13.4
pydantic-core==2.46.4
pydantic-extra-types==2.11.1
pydantic-settings==2.14.2
pygments==2.20.0
pyjwt==2.13.0
python-dotenv==1.2.2
python-json-logger==4.1.0
python-multipart==0.0.32
pyyaml==6.0.3
pyzmq==27.1.0
quack-kernels==0.5.0
referencing==0.37.0
regex==2026.7.19
requests==2.34.2
rich==15.0.0
rich-toolkit==0.20.3
rignore==0.8.0
rpds-py==2026.6.3
safetensors==0.8.0
sentencepiece==0.2.2
sentry-sdk==2.66.0
setproctitle==1.3.7
setuptools==80.10.2
shellingham==1.5.4
six==1.17.0
sniffio==1.3.1
sse-starlette==3.4.5
starlette==1.3.1
supervisor==4.3.0
sympy==1.14.0
tabulate==0.10.0
tiktoken==0.13.0
tilelang==0.1.9
tokenizers==0.22.2
torch==2.11.0+cu129
torch-c-dlpack-ext==0.1.5
torchaudio==2.11.0+cu129
torchvision==0.26.0+cu129
tqdm==4.69.0
transformers==5.14.1
triton==3.6.0
typer==0.27.0
typing-extensions==4.16.0
typing-inspection==0.4.2
urllib3==2.7.0
uvicorn==0.51.0
uvloop==0.22.1
vllm @ https://github.com/vllm-project/vllm/releases/download/v0.20.0/vllm-0.20.0%2Bcu129-cp38-abi3-manylinux_2_31_x86_64.whl
watchfiles==1.2.0
websockets==16.1.1
xgrammar==0.2.3
yarl==1.24.5
z3-solver==4.15.4.0

View File

@@ -0,0 +1,2 @@
42381f4bd1b67710d4068eb8993240930326a804c6e5167b0b78df3420e47c74 /home/admin/cpfs/wjh/aituner/aituner-code-trace-fbaa909/runs/frontier-code-trace-v0/../frontier-qwen30-vllm020-profile-v1/profile_vllm020_flashattn.py
8a7a72b3adb25db6a61a86f9b04d2d19ebbfe3f2d20480852ef2f45376ac3b85 runs/frontier-code-trace-v0/run_flashattn_code_longctx.sh

View File

@@ -0,0 +1 @@
88d34c6409e9fb3c7b8ca0c04756f061d2099eb1

View File

@@ -0,0 +1,564 @@
{
"environment": {
"attention_backend": "FLASH_ATTN",
"block_size": 16,
"dtype": "bfloat16",
"gpu": "NVIDIA H20",
"model": "/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B",
"profile_kv_update": true,
"profile_method": "cuda_event",
"torch_cuda": "12.9",
"torch_version": "2.11.0+cu129",
"vllm_source_commit": "88d34c6409e9fb3c7b8ca0c04756f061d2099eb1",
"vllm_version": "0.20.0"
},
"rows": [
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks48k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.040991999208927155,
"mean_ms": 0.02782719973474741,
"median_ms": 0.025295999832451344,
"min_ms": 0.02412799932062626,
"std_ms": 0.005434033125981124
},
"max_time": 0.011621503829956055,
"mean_time": 0.011469862461090087,
"memory_allocated_mb": 60.0849609375,
"memory_reserved_mb": 62.0,
"min_time": 0.01142630386352539,
"std_time": 5.2644635131708985e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 714219.5495185945
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks64k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03811199963092804,
"mean_ms": 0.02837119996547699,
"median_ms": 0.026176000013947487,
"min_ms": 0.024159999564290047,
"std_ms": 0.004902838828525061
},
"max_time": 0.015688991546630858,
"mean_time": 0.015603910255432129,
"memory_allocated_mb": 68.0888671875,
"memory_reserved_mb": 94.0,
"min_time": 0.01557091236114502,
"std_time": 3.431861179521254e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 524996.6108429873
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks80k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.029759999364614487,
"mean_ms": 0.02612799983471632,
"median_ms": 0.025695999152958393,
"min_ms": 0.024000000208616257,
"std_ms": 0.0019206532069484194
},
"max_time": 0.020114784240722657,
"mean_time": 0.019786701011657717,
"memory_allocated_mb": 76.0927734375,
"memory_reserved_mb": 134.0,
"min_time": 0.019717824935913085,
"std_time": 0.00011854565766692264,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 414015.4538734641
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks96k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.032896000891923904,
"mean_ms": 0.026428800262510776,
"median_ms": 0.02483200002461672,
"min_ms": 0.024159999564290047,
"std_ms": 0.0028081875041272375
},
"max_time": 0.023987648010253906,
"mean_time": 0.023885836791992184,
"memory_allocated_mb": 84.0966796875,
"memory_reserved_mb": 182.0,
"min_time": 0.023849760055541992,
"std_time": 4.082290087440645e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 342964.7481618228
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks112k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03388800099492073,
"mean_ms": 0.02606080025434494,
"median_ms": 0.02440000046044588,
"min_ms": 0.023840000852942467,
"std_ms": 0.003071273491702287
},
"max_time": 0.02814064025878906,
"mean_time": 0.028014582252502435,
"memory_allocated_mb": 92.1005859375,
"memory_reserved_mb": 238.0,
"min_time": 0.027969343185424805,
"std_time": 4.739888751775852e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 292419.138224638
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.02953599952161312,
"mean_ms": 0.025788800045847892,
"median_ms": 0.024800000712275505,
"min_ms": 0.024191999807953835,
"std_ms": 0.002060583463186555
},
"max_time": 0.03218783950805664,
"mean_time": 0.03215217628479004,
"memory_allocated_mb": 100.1044921875,
"memory_reserved_mb": 302.0,
"min_time": 0.03213116836547852,
"std_time": 1.9548439899050275e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 254788.35172583075
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q8ks136k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.032735999673604965,
"mean_ms": 0.02950399983674288,
"median_ms": 0.028351999819278717,
"min_ms": 0.027904000133275986,
"std_ms": 0.0017488521169760844
},
"max_time": 0.03428476715087891,
"mean_time": 0.03422174110412597,
"memory_allocated_mb": 104.1064453125,
"memory_reserved_mb": 370.0,
"min_time": 0.034186080932617186,
"std_time": 3.324003475365458e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 239379.98873506542
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s128k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03446400165557861,
"mean_ms": 0.0248607998713851,
"median_ms": 0.023519999347627163,
"min_ms": 0.0226879995316267,
"std_ms": 0.0035075699446123015
},
"max_time": 0.003272864103317261,
"mean_time": 0.003240902423858643,
"memory_allocated_mb": 66.2958984375,
"memory_reserved_mb": 372.0,
"min_time": 0.003228480100631714,
"std_time": 1.4700871477091224e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 157980.68964705482
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q2ks66k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.03484800085425377,
"mean_ms": 0.02619840018451214,
"median_ms": 0.024639999493956566,
"min_ms": 0.02284800074994564,
"std_ms": 0.0037605668537262792
},
"max_time": 0.005165311813354492,
"mean_time": 0.004916048002243043,
"memory_allocated_mb": 42.04248046875,
"memory_reserved_mb": 372.0,
"min_time": 0.004875135898590088,
"std_time": 8.365277131314812e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 416594.79302593466
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q4ks100k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.023615999147295952,
"mean_ms": 0.018966399878263474,
"median_ms": 0.01788800023496151,
"min_ms": 0.01679999940097332,
"std_ms": 0.0021688374822942504
},
"max_time": 0.0145830717086792,
"mean_time": 0.01451537265777588,
"memory_allocated_mb": 68.06640625,
"memory_reserved_mb": 372.0,
"min_time": 0.014502431869506836,
"std_time": 2.2952325515836057e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 282183.5922900522
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q6ks134k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.028192000463604927,
"mean_ms": 0.021894400380551814,
"median_ms": 0.021088000386953354,
"min_ms": 0.020640000700950623,
"std_ms": 0.0021379161656161685
},
"max_time": 0.024349727630615235,
"mean_time": 0.024299632072448733,
"memory_allocated_mb": 96.09033203125,
"memory_reserved_mb": 372.0,
"min_time": 0.024284608840942384,
"std_time": 2.0842542550131525e-05,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 252843.3344867865
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q1ks8k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.0261439997702837,
"mean_ms": 0.016019200067967178,
"median_ms": 0.01512000011280179,
"min_ms": 0.014368000440299511,
"std_ms": 0.0034013214299104646
},
"max_time": 0.0003514559864997864,
"mean_time": 0.00034397439956665037,
"memory_allocated_mb": 8.5205078125,
"memory_reserved_mb": 372.0,
"min_time": 0.0003375680148601532,
"std_time": 3.760143706773439e-06,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 2976965.731432534
},
{
"attention_core_excludes_kv_cache_update": true,
"config": {
"backend": "FLASH_ATTN",
"batch_spec": "q512s4k",
"block_size": 16,
"device": "cuda:0",
"dtype": "torch.bfloat16",
"head_dim": 128,
"kv_cache_dtype": "auto",
"kv_lora_rank": null,
"num_kv_heads": 1,
"num_kv_splits": null,
"num_layers": 1,
"num_q_heads": 8,
"prefill_backend": null,
"profile_memory": true,
"qk_nope_head_dim": null,
"qk_rope_head_dim": null,
"reorder_batch_threshold": null,
"repeats": 10,
"use_cuda_graphs": false,
"v_head_dim": null,
"warmup_iters": 5
},
"error": null,
"kv_cache_update_time": {
"max_ms": 0.021023999899625778,
"mean_ms": 0.015327999833971262,
"median_ms": 0.014639999717473984,
"min_ms": 0.013856000266969204,
"std_ms": 0.0020222886267191407
},
"max_time": 0.0001605760008096695,
"mean_time": 0.0001493696004152298,
"memory_allocated_mb": 4.265625,
"memory_reserved_mb": 372.0,
"min_time": 0.00014313599467277526,
"std_time": 5.429351067501872e-06,
"tensor_parallel_size": 4,
"throughput_tokens_per_sec": 3427738.9681481416
}
],
"schema_version": "qwen30_vllm020_flashattn_raw.v1"
}