Gahow Wang 99b212e6c1 model/sampling: NaN-safe argmax + optional repetition penalty ...

Make argmax skip NaN logits (warn once) instead of panicking the engine
thread on a single NaN. Add sample_greedy_penalized() applying an
HF-style repetition penalty over recent ids on the greedy path, to break
greedy repetition loops on reasoning models without touching the forward
pass.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-05-31 00:56:27 +08:00

..

src

model/sampling: NaN-safe argmax + optional repetition penalty

2026-05-31 00:56:27 +08:00

Cargo.toml

fix(xserv-chat): UTF-8/CJK-aware line input

2026-05-29 11:36:54 +08:00