← all publishers

Mchenr

@mchenr source repo

Report this profile Claim this profile

• 2 skills
• 0 followers
• 15 hours ago last updated

1. ▌
   Sra Benchmark Cpu Targeting · mchenr bundle

   Find the SRA benchmark model QPS and latency at a target normalized container CPU load, such as "32T 60% CPU", "CPU load target", "capacity point", "QPS at target CPU", or "measure model throughput under a CPU budget". Use for TensorFlow predictor_server/brpc_client benchmark sweeps on wd_dcn, din_mmoe, bst_mmoe, or similar SRA SavedModel workloads when Codex must choose coarse and fine QPS ranges, validate CPU quota normalization, run/interpret benchmark results, and report the target CPU capacity point.
   0 installs
2. ▌
   Sra Benchmark Model Builder · mchenr bundle

   Use when building or modifying SRA benchmark TensorFlow SavedModels for predictor-server hardware inference benchmarking, especially when deriving train/export scripts and inference TSV generators from pbtxt/reference graphs such as wd_dcn or wide_and_deep.
   0 installs