popov/neuron-tai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add live endpoint benchmark runner

Browse Source
This commit is contained in:
Dobromir Popov
2026-07-14 22:46:11 +03:00
parent e6f6782995
commit a508768e8a
3 changed files with 136 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
.scratch/distributed-gguf-runtime/evidence/DGR-001/README.md
View File

@@ -63,8 +63,9 @@ Result: passed
## Limitations
- This slice captures the DGR-001 contract and baseline selection only.
- It does **not** download or run a real model yet.
- This slice still uses a deterministic stub backend for the core comparison matrix.
- It now also includes a live endpoint runner that can fan out one OpenAI-compatible request per lane when the caller provides endpoints.
- It does **not** download or run a real model from within the repo.
- Real safetensors vs GGUF execution, TTFT/prefill/decode measurements, RSS/VRAM capture, and output-drift comparison are still to be implemented against the contract.
## Compatibility notes