thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 6

graph : fix KQ mask, lora, cvec reuse checks (#19644)

Browse source 
* graph : fix KQ mask reuse condition

* cont : dedup KQ mask build and can_reuse

* cont : fix build

* graph : fix adapter check for reuse
This commit is contained in:
Georgi Gerganov 2026-02-16 09:21:11 +02:00 • committed by GitHub
parent 267ba5a1d9
commit d5dfc33027
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 67 additions and 54 deletions
Download patch file Download diff file Expand all files Collapse all files

7
src/llama-context.h
View file

@ -256,9 +256,10 @@ private:
const llama_model & model;
llama_cparams cparams;
llama_adapter_cvec cvec;
llama_adapter_loras loras;
llama_cparams cparams;
llama_adapter_cvec_ptr cvec;
llama_adapter_loras_ptr loras;
llama_cross cross; // TODO: tmp for handling cross-attention - need something better probably