mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-14 13:04:08 +00:00

Files

Georgi Gerganov f64d56bcd8 llama-server-simulator : replace Flask with stdlib http.server

- Use HTTPServer + BaseHTTPRequestHandler instead of Flask
- RequestHandler handles POST /v1/chat/completions
- Server runs in daemon thread with clean Ctrl+C shutdown
- Remove flask and unused asdict imports

Assisted-by: llama.cpp:local pi

2026-05-10 20:47:08 +03:00

llama-eval.py

llama-eval : support multiple evaluation endpoints with dynamic task distribution

2026-05-10 20:42:23 +03:00

llama-server-simulator.py

llama-server-simulator : replace Flask with stdlib http.server

2026-05-10 20:47:08 +03:00

README.md

remove junk

2026-05-10 18:13:50 +03:00

test-simulator.sh

test : fix path

2026-05-10 18:13:46 +03:00

README.md

llama-eval

Simple evaluation tool for llama.cpp with support for multiple datasets.

TODO: add usage