Files
vllm-omni/benchmarks/tts/evidence/breeze_tts_2_20260918.json
T

758 lines
22 KiB
JSON

{
"measurement_scope": "Historical measurements for PR7752, not a main-branch comparison or a measurement of subsequent review fixes.",
"environment": {
"gpu": "NVIDIA H100 80 GB",
"gpu_count": 1,
"python": "3.12",
"pytorch": "2.13.0+cu132",
"vllm": "0.29.0",
"transformers": "5.14.1",
"nsight_systems": "2026.5.1"
},
"model": {
"id": "BreezeBlue/Breeze-TTS-2",
"revision": "3e28c5151381a722f1d8661b4118c298caa77aa4"
},
"workload": {
"texts": [
"Hello, this is Breeze TTS 2 running on vLLM Omni.",
"你好,今天天气很好,我们一起出去走走吧。"
],
"alternating_texts": true,
"seed": 42,
"guidance_scale": 1.0,
"repetition_penalty": 1.1,
"top_p": 1.0,
"sampled": {
"temperature": 0.9,
"top_k": 50
},
"greedy": {
"temperature": 0.0,
"top_k": 0
},
"stream": false,
"response_format": "pcm",
"sample_rate": 24000,
"channels": 1,
"pcm_bits": 16
},
"cumulative_diagnostic": {
"baseline_sha": "5bda85c371e8c0c7728c2f7f5865d3ddd79b9d99",
"combined_sha": "37a04897cf8566c63e82eb13c27c064b9bcd4222",
"intermediate_variants": "Ordered patch subsets of the combined commit, not independent commits.",
"patch_sha256": {
"batched_eos": "2f107ea8e890e03cc138ef2f69e693e3474d3aaf0eb4051c00886cbaa9785b3d",
"greedy_graph": "4e783313260ddc2e36c8a74ba9d95dc5d78338443612ebf89854e31b8be6933b",
"batched_embedding": "90557e4ec73fdedcff51fd717d5e8c6477e71087fd97ac52534542234f5d1d3a"
},
"sequence_slots": 8,
"kv_gib": 2,
"codec_chunk_frames": 16,
"max_new_tokens": 48,
"temperature": 0.0,
"cohorts_per_variant": 1,
"nsight_injection_present": true,
"collection_enabled": false,
"warmup": "Two eight-request full-response warmups, then four full-response 64-request cohorts, each preceded by one concurrency-sized warmup.",
"variants": [
{
"variant": "baseline",
"makespan_s": 0.9672094583511353,
"requests": 8,
"concurrency": 8,
"audio_s": 30.72,
"failures": 0
},
{
"variant": "plus_batched_eos",
"makespan_s": 0.9280132218264043,
"requests": 8,
"concurrency": 8,
"audio_s": 30.72,
"failures": 0
},
{
"variant": "plus_greedy_graph",
"makespan_s": 0.8857334200292826,
"requests": 8,
"concurrency": 8,
"audio_s": 30.72,
"failures": 0
},
{
"variant": "plus_batched_embedding",
"makespan_s": 0.8435833756811917,
"requests": 8,
"concurrency": 8,
"audio_s": 30.72,
"failures": 0
}
],
"limits": [
"Single cumulative diagnostic samples; no repeat spread.",
"Nsight injection remains when collection is disabled.",
"The final variant used graph tracing configuration; prior variants used node tracing configuration.",
"Do not interpret these timings as isolated uninstrumented per-optimization gains."
]
},
"mechanical_attribution": {
"batched_eos": {
"stage0_stream_synchronization_calls": [
773,
438
],
"device_to_host_copies": [
841,
506
],
"capture_mode": "node"
},
"greedy_graph": {
"radix_sort_kernels": [
735,
0
],
"capture_mode": "node"
},
"combined_graph_capture": {
"captured_wall_ms": [
955.4114495404065,
855.6996420957148
],
"gpu_envelope_ms": [
926.633897,
826.396835
],
"activity_upper_ms": [
651.130806,
628.864685
],
"idle_lower_ms": [
275.50309100000004,
197.53215
],
"stage0_explicit_kernel_launch_count": [
7087,
6198
],
"stage0_graph_launch_count": [
156,
156
]
},
"limits": [
"Host API durations overlap GPU activity and are not additional idle time.",
"Graph envelopes hide internal gaps: activity is an upper bound and idle is a lower bound.",
"Stage 1 has eight versus nine graph launches across the graph-mode traces.",
"No separate final-capacity stage breakdown was measured."
]
},
"combined_uninstrumented_ab": {
"baseline_sha": "5bda85c371e8c0c7728c2f7f5865d3ddd79b9d99",
"head_sha": "37a04897cf8566c63e82eb13c27c064b9bcd4222",
"sequence_slots": 8,
"kv_gib": 2,
"codec_chunk_frames": 16,
"requests_per_group": 64,
"max_new_tokens": 384,
"baseline_rounds": 2,
"head_rounds": 1,
"profiler_configured": false,
"nsight_injection_present": false,
"warmup": "One excluded 64-request full-response wave for each temperature/concurrency family, plus an excluded 2*C-request full-response cohort before every group.",
"rows": [
{
"build": "plain-baseline",
"phase": "round-0",
"temperature": 0.0,
"concurrency": 8,
"requests": 64,
"makespan_s": 10.77213971177116,
"req_per_s": 5.941252314994074,
"aggregate_rtf": 0.030157166046391827,
"audio_s": 357.2,
"caps": 0,
"failures": 0,
"endpoint_trimmed_audio_s": 305.88,
"endpoint_trimmed_aggregate_rtf": 0.03521688149526337,
"quiet_tail_at_least_3s": 7,
"max_quiet_tail_s": 3.24
},
{
"build": "plain-baseline",
"phase": "round-0",
"temperature": 0.0,
"concurrency": 16,
"requests": 64,
"makespan_s": 11.076066234149039,
"req_per_s": 5.778224745774739,
"aggregate_rtf": 0.029092420240988227,
"audio_s": 380.72,
"caps": 2,
"failures": 0,
"endpoint_trimmed_audio_s": 315.48,
"endpoint_trimmed_aggregate_rtf": 0.035108616185333584,
"quiet_tail_at_least_3s": 6,
"max_quiet_tail_s": 26.04
},
{
"build": "plain-baseline",
"phase": "round-0",
"temperature": 0.9,
"concurrency": 8,
"requests": 64,
"makespan_s": 8.603743681218475,
"req_per_s": 7.438622345259851,
"aggregate_rtf": 0.03389435739528236,
"audio_s": 253.84,
"caps": 0,
"failures": 0,
"endpoint_trimmed_audio_s": 239.02,
"endpoint_trimmed_aggregate_rtf": 0.035995915325991445,
"quiet_tail_at_least_3s": 0,
"max_quiet_tail_s": 1.3
},
{
"build": "plain-baseline",
"phase": "round-0",
"temperature": 0.9,
"concurrency": 16,
"requests": 64,
"makespan_s": 8.66502623911947,
"req_per_s": 7.386013409984042,
"aggregate_rtf": 0.033143460216950235,
"audio_s": 261.44,
"caps": 0,
"failures": 0,
"endpoint_trimmed_audio_s": 242.14,
"endpoint_trimmed_aggregate_rtf": 0.03578519137325296,
"quiet_tail_at_least_3s": 0,
"max_quiet_tail_s": 1.3
},
{
"build": "plain-baseline",
"phase": "round-1",
"temperature": 0.0,
"concurrency": 8,
"requests": 64,
"makespan_s": 13.904579282738268,
"req_per_s": 4.602800178172402,
"aggregate_rtf": 0.0392784725501081,
"audio_s": 354.0,
"caps": 1,
"failures": 0,
"endpoint_trimmed_audio_s": 285.36,
"endpoint_trimmed_aggregate_rtf": 0.048726448285457906,
"quiet_tail_at_least_3s": 8,
"max_quiet_tail_s": 25.38
},
{
"build": "plain-baseline",
"phase": "round-1",
"temperature": 0.0,
"concurrency": 16,
"requests": 64,
"makespan_s": 10.060411099344492,
"req_per_s": 6.361569061941222,
"aggregate_rtf": 0.02935460754944121,
"audio_s": 342.72,
"caps": 0,
"failures": 0,
"endpoint_trimmed_audio_s": 289.04,
"endpoint_trimmed_aggregate_rtf": 0.03480629359031446,
"quiet_tail_at_least_3s": 10,
"max_quiet_tail_s": 3.16
},
{
"build": "plain-baseline",
"phase": "round-1",
"temperature": 0.9,
"concurrency": 8,
"requests": 64,
"makespan_s": 8.535738762002438,
"req_per_s": 7.4978864494894575,
"aggregate_rtf": 0.033363581777683074,
"audio_s": 255.84,
"caps": 0,
"failures": 0,
"endpoint_trimmed_audio_s": 237.9,
"endpoint_trimmed_aggregate_rtf": 0.03587952401009852,
"quiet_tail_at_least_3s": 0,
"max_quiet_tail_s": 2.12
},
{
"build": "plain-baseline",
"phase": "round-1",
"temperature": 0.9,
"concurrency": 16,
"requests": 64,
"makespan_s": 8.584469985216856,
"req_per_s": 7.4553234049642105,
"aggregate_rtf": 0.033355882752629996,
"audio_s": 257.36,
"caps": 0,
"failures": 0,
"endpoint_trimmed_audio_s": 242.57999999999998,
"endpoint_trimmed_aggregate_rtf": 0.035388201769382704,
"quiet_tail_at_least_3s": 0,
"max_quiet_tail_s": 1.94
},
{
"build": "plain-batched",
"phase": "round-0",
"temperature": 0.0,
"concurrency": 8,
"requests": 64,
"makespan_s": 12.983129982370883,
"req_per_s": 4.929473870083891,
"aggregate_rtf": 0.03320153943936907,
"audio_s": 391.04,
"caps": 2,
"failures": 0,
"endpoint_trimmed_audio_s": 312.72,
"endpoint_trimmed_aggregate_rtf": 0.041516788124747,
"quiet_tail_at_least_3s": 11,
"max_quiet_tail_s": 28.4
},
{
"build": "plain-batched",
"phase": "round-0",
"temperature": 0.0,
"concurrency": 16,
"requests": 64,
"makespan_s": 9.772029620129615,
"req_per_s": 6.549304749155183,
"aggregate_rtf": 0.027698496655696188,
"audio_s": 352.8,
"caps": 1,
"failures": 0,
"endpoint_trimmed_audio_s": 286.26,
"endpoint_trimmed_aggregate_rtf": 0.034136902187275955,
"quiet_tail_at_least_3s": 6,
"max_quiet_tail_s": 26.04
},
{
"build": "plain-batched",
"phase": "round-0",
"temperature": 0.9,
"concurrency": 8,
"requests": 64,
"makespan_s": 8.171920725144446,
"req_per_s": 7.831696140061215,
"aggregate_rtf": 0.03169376638669115,
"audio_s": 257.84,
"caps": 0,
"failures": 0,
"endpoint_trimmed_audio_s": 241.72,
"endpoint_trimmed_aggregate_rtf": 0.03380738344011437,
"quiet_tail_at_least_3s": 0,
"max_quiet_tail_s": 1.22
},
{
"build": "plain-batched",
"phase": "round-0",
"temperature": 0.9,
"concurrency": 16,
"requests": 64,
"makespan_s": 8.02551719499752,
"req_per_s": 7.974563937124526,
"aggregate_rtf": 0.030886380830501534,
"audio_s": 259.84000000000003,
"caps": 0,
"failures": 0,
"endpoint_trimmed_audio_s": 243.0,
"endpoint_trimmed_aggregate_rtf": 0.03302681973250008,
"quiet_tail_at_least_3s": 0,
"max_quiet_tail_s": 1.78
}
],
"limits": [
"Ranges compare the head sample with two baseline samples; they are not confidence intervals.",
"Full-response greedy output lengths and frame-limit incidence vary, so no general greedy throughput gain is claimed.",
"No transcription was run on these historical A/B outputs."
]
},
"capacity": {
"runtime_sha": "7bc0b3e3a2e41ef44e8efb30fd927e93bf6a48a7",
"main_base_sha": "6bda549ac23a667efbe44a54cf3f6d57e6e24da2",
"sequence_slots": [
8,
16,
32
],
"kv_gib": [
2,
4,
8
],
"codec_graph_buckets": [
[
1,
2,
4,
8
],
[
1,
2,
4,
8,
16
],
[
1,
2,
4,
8,
16,
32
]
],
"backbone_capture_sizes": [
1,
2,
4,
8,
32,
64,
128,
256
],
"codec_chunk_frames": 16,
"requests_per_group": 128,
"cohorts_per_point": 1,
"excluded_warmups_per_configuration": {
"cohorts": 4,
"requests_per_cohort": 64,
"covers": "Both client concurrency levels and both sampling settings"
},
"profiler_configured": false,
"nsight_injection_present": false,
"rows": [
{
"slots": 8,
"concurrency": 8,
"observed_peak_client_requests": 8,
"temperature": 0.0,
"max_new_tokens": 384,
"requests": 128,
"failures": 0,
"req_per_s": 6.7812081269297915,
"makespan_s": 18.87569259107113,
"aggregate_rtf": 0.02841355459879445,
"audio_s": 664.32,
"near_cap_count": 0,
"exact_cap_count": 0,
"fixed48_verified": null
},
{
"slots": 8,
"concurrency": 16,
"observed_peak_client_requests": 16,
"temperature": 0.0,
"max_new_tokens": 384,
"requests": 128,
"failures": 0,
"req_per_s": 5.8798058352164615,
"makespan_s": 21.76942633604631,
"aggregate_rtf": 0.029975526459636356,
"audio_s": 726.24,
"near_cap_count": 2,
"exact_cap_count": 2,
"fixed48_verified": null
},
{
"slots": 8,
"concurrency": 8,
"observed_peak_client_requests": 8,
"temperature": 0.9,
"max_new_tokens": 384,
"requests": 128,
"failures": 0,
"req_per_s": 7.72991106982811,
"makespan_s": 16.559052082709968,
"aggregate_rtf": 0.0320365502296664,
"audio_s": 516.88,
"near_cap_count": 0,
"exact_cap_count": 0,
"fixed48_verified": null
},
{
"slots": 8,
"concurrency": 16,
"observed_peak_client_requests": 16,
"temperature": 0.9,
"max_new_tokens": 384,
"requests": 128,
"failures": 0,
"req_per_s": 7.945057322591292,
"makespan_s": 16.110645248088986,
"aggregate_rtf": 0.030958196095482296,
"audio_s": 520.4,
"near_cap_count": 0,
"exact_cap_count": 0,
"fixed48_verified": null
},
{
"slots": 8,
"concurrency": 8,
"observed_peak_client_requests": 8,
"temperature": 0.0,
"max_new_tokens": 48,
"requests": 128,
"failures": 0,
"req_per_s": 9.850579526557848,
"makespan_s": 12.994159344118088,
"aggregate_rtf": 0.026436684863521503,
"audio_s": 491.52,
"near_cap_count": 128,
"exact_cap_count": 128,
"fixed48_verified": true
},
{
"slots": 8,
"concurrency": 16,
"observed_peak_client_requests": 16,
"temperature": 0.0,
"max_new_tokens": 48,
"requests": 128,
"failures": 0,
"req_per_s": 10.665146583658053,
"makespan_s": 12.00171033712104,
"aggregate_rtf": 0.02441754218978076,
"audio_s": 491.52,
"near_cap_count": 128,
"exact_cap_count": 128,
"fixed48_verified": true
},
{
"slots": 16,
"concurrency": 16,
"observed_peak_client_requests": 16,
"temperature": 0.0,
"max_new_tokens": 384,
"requests": 128,
"failures": 0,
"req_per_s": 7.754874623816668,
"makespan_s": 16.505747186020017,
"aggregate_rtf": 0.023979758231665527,
"audio_s": 688.32,
"near_cap_count": 1,
"exact_cap_count": 1,
"fixed48_verified": null
},
{
"slots": 16,
"concurrency": 32,
"observed_peak_client_requests": 32,
"temperature": 0.0,
"max_new_tokens": 384,
"requests": 128,
"failures": 0,
"req_per_s": 10.104109318018903,
"makespan_s": 12.668113138061017,
"aggregate_rtf": 0.018577125085143444,
"audio_s": 681.92,
"near_cap_count": 1,
"exact_cap_count": 1,
"fixed48_verified": null
},
{
"slots": 16,
"concurrency": 16,
"observed_peak_client_requests": 16,
"temperature": 0.9,
"max_new_tokens": 384,
"requests": 128,
"failures": 0,
"req_per_s": 10.920674745703012,
"makespan_s": 11.72088748915121,
"aggregate_rtf": 0.021831484669108944,
"audio_s": 536.88,
"near_cap_count": 0,
"exact_cap_count": 0,
"fixed48_verified": null
},
{
"slots": 16,
"concurrency": 32,
"observed_peak_client_requests": 32,
"temperature": 0.9,
"max_new_tokens": 384,
"requests": 128,
"failures": 0,
"req_per_s": 11.210975235811437,
"makespan_s": 11.417383172083646,
"aggregate_rtf": 0.02120613516360261,
"audio_s": 538.4,
"near_cap_count": 0,
"exact_cap_count": 0,
"fixed48_verified": null
},
{
"slots": 16,
"concurrency": 16,
"observed_peak_client_requests": 16,
"temperature": 0.0,
"max_new_tokens": 48,
"requests": 128,
"failures": 0,
"req_per_s": 15.14487085057202,
"makespan_s": 8.451706274878234,
"aggregate_rtf": 0.017195040435543284,
"audio_s": 491.52,
"near_cap_count": 128,
"exact_cap_count": 128,
"fixed48_verified": true
},
{
"slots": 16,
"concurrency": 32,
"observed_peak_client_requests": 32,
"temperature": 0.0,
"max_new_tokens": 48,
"requests": 128,
"failures": 0,
"req_per_s": 16.563937910502617,
"makespan_s": 7.727630995213985,
"aggregate_rtf": 0.015721905507840955,
"audio_s": 491.52,
"near_cap_count": 128,
"exact_cap_count": 128,
"fixed48_verified": true
},
{
"slots": 32,
"concurrency": 32,
"observed_peak_client_requests": 32,
"temperature": 0.0,
"max_new_tokens": 384,
"requests": 128,
"failures": 0,
"req_per_s": 15.246181432777554,
"makespan_s": 8.395544849336147,
"aggregate_rtf": 0.012390119317202106,
"audio_s": 677.6,
"near_cap_count": 0,
"exact_cap_count": 0,
"fixed48_verified": null
},
{
"slots": 32,
"concurrency": 64,
"observed_peak_client_requests": 64,
"temperature": 0.0,
"max_new_tokens": 384,
"requests": 128,
"failures": 0,
"req_per_s": 11.166074835908939,
"makespan_s": 11.463294119108468,
"aggregate_rtf": 0.015826284127331107,
"audio_s": 724.32,
"near_cap_count": 1,
"exact_cap_count": 1,
"fixed48_verified": null
},
{
"slots": 32,
"concurrency": 32,
"observed_peak_client_requests": 32,
"temperature": 0.9,
"max_new_tokens": 384,
"requests": 128,
"failures": 0,
"req_per_s": 17.17219888865503,
"makespan_s": 7.453908543102443,
"aggregate_rtf": 0.014336645143680651,
"audio_s": 519.92,
"near_cap_count": 0,
"exact_cap_count": 0,
"fixed48_verified": null
},
{
"slots": 32,
"concurrency": 64,
"observed_peak_client_requests": 64,
"temperature": 0.9,
"max_new_tokens": 384,
"requests": 128,
"failures": 0,
"req_per_s": 17.514343665613783,
"makespan_s": 7.3082955572754145,
"aggregate_rtf": 0.013677750331777613,
"audio_s": 534.32,
"near_cap_count": 0,
"exact_cap_count": 0,
"fixed48_verified": null
},
{
"slots": 32,
"concurrency": 32,
"observed_peak_client_requests": 32,
"temperature": 0.0,
"max_new_tokens": 48,
"requests": 128,
"failures": 0,
"req_per_s": 25.82908453652114,
"makespan_s": 4.955653763841838,
"aggregate_rtf": 0.010082303393232905,
"audio_s": 491.52,
"near_cap_count": 128,
"exact_cap_count": 128,
"fixed48_verified": true
},
{
"slots": 32,
"concurrency": 64,
"observed_peak_client_requests": 64,
"temperature": 0.0,
"max_new_tokens": 48,
"requests": 128,
"failures": 0,
"req_per_s": 28.81314277607874,
"makespan_s": 4.442417163401842,
"aggregate_rtf": 0.00903812085653044,
"audio_s": 491.52,
"near_cap_count": 128,
"exact_cap_count": 128,
"fixed48_verified": true
}
],
"limits": [
"This scales slots, KV reservation and codec graph buckets together.",
"One cohort per point; no repeated capacity samples or confidence intervals.",
"The 48-frame cohorts deliberately truncate speech and are excluded from full-utterance quality claims.",
"Peak device memory was not measured.",
"No capacity claim extends to cloning, CFG guidance above one, long prompts or other GPUs."
]
},
"quality": {
"full_response_pcm_checked": 1536,
"sampled_full_responses": 768,
"sampled_frame_limit_hits": 0,
"sampled_quiet_tails_at_least_three_seconds": 0,
"greedy_frame_limit_hits": 5,
"asr_selected_unique_clips": 47,
"asr_selected_sampled_clips": 24,
"sampled_asr": "All selected sampled transcripts matched after accounting for TTS 2 versus TTS2 spacing.",
"endpoint_method": "Trim leading/trailing quiet using 20 ms RMS windows at or below -40 dBFS; keep internal pauses and original makespans.",
"limits": [
"ASR selects median-duration and longest English/Chinese clips per group, deduplicated by WAV hash.",
"Selected ASR and endpoint measurements do not establish perceptual quality parity.",
"Capped greedy clips have extra ASR words with unreliable tail alignment.",
"No listening or MOS assessment was performed."
]
},
"metrics": {
"requests_per_second": "Completed requests divided by cohort wall time",
"aggregate_rtf": "Cohort wall time divided by total returned audio duration",
"timing_exclusions": [
"PCM validation",
"hashing",
"WAV file writes",
"post-timing audio analysis"
]
}
}