EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

llama : bump max seq limit from 64 to 256 (#15916)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-09-18 12:47:56 +03:00
committed by GitHub
parent b213fce89b
commit e58174cecb
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-cparams.h
View File

@@ -4,7 +4,7 @@
#include <cstdint> #include <cstdint>
#define LLAMA_MAX_SEQ 64 #define LLAMA_MAX_SEQ 256
struct llama_cparams { struct llama_cparams {
uint32_t n_ctx; // context size used during inference uint32_t n_ctx; // context size used during inference