fix(ds4): honor sampler settings in decode

[dusterbloom]

Summary

• thread GenerateRequest.sampler into DeepSeek4Backend::generate_impl
• sample from logits when temperature or penalty settings are active
• keep the existing greedy argmax fast path when the sampler is inert

Why

DeepSeek4 single-device decode was always using greedy argmax and never reading the request sampler, so temperature / top-k / top-p / repetition settings were silently ignored.

Validation

• git diff --check
• manual source inspection of the decode path