Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

speculative decoding initial impl completed (+6 squashed commit)

Browse Source 
Squashed commit:

[0a6306ca0] draft wip dont use (will be squashed)

[a758a1c9c] wip dont use (will be squashed)

[e1994d3ce] wip dont use

[f59690d68] wip

[77228147d] wip on spec decoding. dont use yet

[2445bca54] wip adding speculative decoding (+1 squashed commits)

Squashed commits:

[50e341bb7] wip adding speculative decoding
This commit is contained in:
Concedo
2024-11-27 00:16:51 +08:00
parent b9e99c69e8
commit f75bbb945f
9 changed files with 539 additions and 280 deletions
Download Patch File Download Diff File Expand all files Collapse all files
expose.h
+2
View File
@@ -40,6 +40,7 @@ struct load_model_inputs
const char * model_filename = nullptr;
const char * lora_filename = nullptr;
const char * lora_base = nullptr;
const char * draftmodel_filename = nullptr;
const char * mmproj_filename = nullptr;
const bool use_mmap = false;
const bool use_mlock = false;
@@ -197,6 +198,7 @@ extern std::string executable_path;
extern std::string lora_filename;
extern std::string lora_base;
extern std::string mmproj_filename;
extern std::string draftmodel_filename;
extern std::vector<std::string> generated_tokens;
extern bool generation_finished;
extern float last_eval_time;