Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-08 13:59:03 +02:00
Code Issues Packages Projects Releases Wiki Activity

cont : naming

Browse Source
This commit is contained in:
Georgi Gerganov
2026-01-25 21:15:15 +02:00
parent 924517dd38
commit 9ac881767c
2 changed files with 143 additions and 158 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-context.cpp
+4 -4
View File
@@ -2035,9 +2035,10 @@ private:
GGML_ABORT("not supported by multimodal");
}
struct common_speculative_params params_spec;
params_spec.n_draft = n_draft_max;
params_spec.p_min = slot.task->params.speculative.p_min;
struct common_speculative_params params_spec = {
/*.params_spec.n_draft =*/ n_draft_max,
/*.params_spec.p_min =*/ slot.task->params.speculative.p_min,
};
const llama_tokens & cached_text_tokens = slot.prompt.tokens.get_text_tokens();
llama_tokens draft = common_speculative_gen_draft(slot.spec, params_spec, cached_text_tokens, slot.sampled);
@@ -2814,7 +2815,6 @@ private:
SLT_DBG(slot, "accepted %d/%d draft tokens, new n_tokens = %d\n", (int) ids.size() - 1, (int) n_draft, slot.prompt.n_tokens());
}
}
SRV_DBG("%s", "run slots completed\n");