| { |
| "format": "bit-jev-epyc9654-cpu32-case-v1", |
| "publication_status": "public_sanitized_case_study", |
| "checkpoint": { |
| "name": "bit-jev-2b-distilled", |
| "cpu_format": "I2_S GGUF with float32 pointer head", |
| "cpu_gguf_sha256": "731700ba3112e35dc9bbecf54fe97b79d91b69246d765413ce683e06250773ff", |
| "head_f32_sha256": "a3b3df8f5d4803d575e64c4f15e8ab09c00762e4140917c07925705ba43c1b27" |
| }, |
| "workload": { |
| "questions": 1, |
| "input_tokens": 703, |
| "options": 77, |
| "encoded_input_sha256": "2d2921d9d0e46c1540f71c283b07668ff0fe8ac5d2fa52911588f65d0be4c9c6", |
| "input_contents_included": false |
| }, |
| "hardware": { |
| "cpu": "AMD EPYC 9654 96-Core Processor", |
| "platform": "AutoDL Ubuntu 22.04 container, Linux x86_64", |
| "host_logical_cpus_visible_to_lscpu": 192, |
| "container_cpu_quota_cores": 32, |
| "container_cpuset": "64-95", |
| "numa_nodes_visible": 1 |
| }, |
| "build": { |
| "project_commit": "4272aacc0cabc167077e61df86acaedfab5fd35f", |
| "bitnet_commit": "0b341e582afbf9e1011f24744b554c96a3477eb5", |
| "llama_cpp_commit": "390c307752ab78fd8189f359d6954c9ba1be74af", |
| "cmake": "3.31.10", |
| "compiler": "g++ 11.4.0", |
| "configuration": "Release, GGML_NATIVE=ON, GGML_OPENMP=ON, Vulkan=OFF, CUDA=OFF", |
| "native_binary_sha256": "8f24ada846ab1f30b2b1ae4ac0a35d007747d3a95f5ae1c6cf66b465e5081077" |
| }, |
| "timing_protocol": { |
| "native_runner_threads": 32, |
| "batch": 128, |
| "process_launches": 2, |
| "requests_per_launch": 3, |
| "model_loading_included_in_native_latency": false, |
| "explicit_cpu_warmup": false, |
| "same_encoded_request_repeated": true |
| }, |
| "measurement": { |
| "path": "native_cpu_i2_s_32_threads", |
| "inference_ms_by_launch": [ |
| [1979.920258, 1946.525392, 1949.816113], |
| [1971.828346, 1949.075305, 1929.623975] |
| ], |
| "peak_process_rss_mib_by_launch": [1625.8828125, 1625.7265625] |
| }, |
| "diagnostic_16_thread_run": { |
| "inference_ms": [3225.943667, 3196.725099, 3207.690814], |
| "peak_process_rss_mib": 1623.09375 |
| }, |
| "comparison_boundary": { |
| "historical_gpu_source": "bit-jev-autodl-case-2026-09-27.json", |
| "gpu_hardware": "NVIDIA GeForce RTX 5090 on a different AutoDL host", |
| "gpu_path": "experimental FP16 mixed-precision PyTorch", |
| "note": "The speed figure juxtaposes deployment paths measured on different hosts and weight formats. It is not an isolated CPU-versus-GPU hardware speedup." |
| }, |
| "rights_note": "The training set included Yelp review records. The maintainer directed publication of sanitized timing aggregates; no request text, options, prediction, or raw review record is included. No written Yelp response had been received on 2026-09-28." |
| } |
|
|
