Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

server : fix draft model fit vs load inconsistency (#25056)

Browse Source 
* fix: draft model fit vs load inconsistency

* refactor(server): unify draft/mtp parameter initialization, model, and context load
- moves speculative init to speculative.cpp
- changes server_context_impl model_dft and ctx_dft to use raw pointers

- fix: don't throttle progress callback when loading draft model
- refactor: rename draft model/ctx load method

* fix: valign
This commit is contained in:
Alex
2026-07-07 17:20:42 +03:00
committed by GitHub
parent 5eca4e3cab
commit f5525f7e7a
3 changed files with 176 additions and 107 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/speculative.h
+18
View File
@@ -23,6 +23,8 @@ std::string common_speculative_type_to_str(enum common_speculative_type type);
// return the max number of draft tokens based on the speculative parameters
int32_t common_speculative_n_max(const common_params_speculative * spec);
common_params common_base_params_to_speculative(const common_params & params);
common_speculative * common_speculative_init(common_params_speculative & params, uint32_t n_seq);
void common_speculative_free(common_speculative * spec);
@@ -80,3 +82,19 @@ struct common_speculative_deleter {
};
typedef std::unique_ptr<common_speculative, common_speculative_deleter> common_speculative_ptr;
struct common_init_speculative_result {
common_init_speculative_result(common_params & params, llama_model * model_tgt, llama_context * ctx_tgt);
~common_init_speculative_result();
llama_model * model();
llama_context * context();
private:
struct impl;
std::unique_ptr<impl> pimpl;
};
using common_init_speculative_result_ptr = std::unique_ptr<common_init_speculative_result>;
common_init_speculative_result_ptr common_init_speculative_from_params(common_params & params, llama_model * model_tgt, llama_context * ctx_tgt);