| { |
| "hardware": "NVIDIA RTX PRO 6000 Blackwell Server Edition", |
| "validation_samples": 6119, |
| "validation_seed": 43, |
| "validation": { |
| "fast-code-pruner": { |
| "loss": 0.2731010076982715, |
| "compression_loss": 0.2731010076982715, |
| "accuracy": 0.859388530254364, |
| "precision": 0.8149362802505493, |
| "recall": 0.8348633646965027, |
| "f1": 0.8247794508934021 |
| } |
| }, |
| "serving": { |
| "date_utc": "2026-07-28", |
| "backend": "vLLM 0.13.0", |
| "checkpoint": "001-kd-search-weight-0.4-ac3262", |
| "requests_per_repeat": 1000, |
| "unique_validation_examples": 100, |
| "repeats": 3, |
| "prefix_caching": false, |
| "hugging_face": { |
| "requests_per_repeat": 100, |
| "warmup_requests": 10, |
| "repeats": 3, |
| "max_model_length": 8192, |
| "serialized_requests": true, |
| "concurrency_1": { |
| "requests_per_second_runs": [ |
| 15.635215615008196, |
| 16.014152944551167, |
| 16.04293924256032 |
| ], |
| "requests_per_second_median": 16.014152944551167 |
| }, |
| "concurrency_16": { |
| "requests_per_second_runs": [ |
| 15.961968793509204, |
| 16.049117711074377, |
| 16.03105236128065 |
| ], |
| "requests_per_second_median": 16.03105236128065 |
| } |
| }, |
| "concurrency_1": { |
| "requests_per_second_runs": [ |
| 77.85959605324707, |
| 79.01445520339735, |
| 79.55801844550992 |
| ], |
| "requests_per_second_median": 79.01445520339735, |
| "model_input_tokens_per_second_median": 56078.92929150719, |
| "latency_p50_ms_median": 11.922281002625823, |
| "latency_p95_ms_median": 16.762261977419257 |
| }, |
| "concurrency_16": { |
| "requests_per_second_runs": [ |
| 139.21897948711825, |
| 143.42106837168544, |
| 143.6922866973871 |
| ], |
| "requests_per_second_median": 143.42106837168544, |
| "model_input_tokens_per_second_median": 101790.2348554363, |
| "latency_p50_ms_median": 108.39256300823763, |
| "latency_p95_ms_median": 160.10672401171178 |
| }, |
| "concurrency_64": { |
| "requests_per_second_runs": [ |
| 172.7439921722694, |
| 174.6905065239383, |
| 172.40774004660466 |
| ], |
| "requests_per_second_median": 172.7439921722694, |
| "model_input_tokens_per_second_median": 122601.59356442477, |
| "latency_p50_ms_median": 369.8863319878001, |
| "latency_p95_ms_median": 497.7567640016787 |
| } |
| } |
| } |
|
|