sampler : remove "full-context windows" from history-based samplers (#26524)

* Resolve -1 to 1024 instead of ctx-len for samplers Because of backend-sampling we initialize samplers before the complete llama_context is there. Therefore, we cannot infer the resolved context length yet at the time we construct the samplers. * Shared default of 64 for history-based samplers, remove context_size
2026-08-04 21:28:55 +03:00
parent 76c956c137
commit a6aa6f5450
18 changed files with 52 additions and 80 deletions
@@ -98,7 +98,6 @@ std::vector<std::unique_ptr<field>> make_llama_cmpl_schema(
 task_params eval_llama_cmpl_schema(
                    const llama_vocab * vocab,
                    const common_params & params_base,
-                    const int n_ctx_slot,
                    const std::vector<llama_logit_bias> & logit_bias_eog,
                    const json & data);