vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

common : fix context shift help message (#15448)

Browse source 
Signed-off-by: Jie Fu <jiefu@tencent.com>
This commit is contained in:
Jie Fu (傅杰) 2025-08-20 18:33:30 +08:00 • committed by GitHub
parent 1a99c2d948
commit ec5ab1a36c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/arg.cpp
View file

@ -1532,7 +1532,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_PERPLEXITY}).set_env("LLAMA_ARG_NO_CONTEXT_SHIFT")); ).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_PERPLEXITY}).set_env("LLAMA_ARG_NO_CONTEXT_SHIFT"));
add_opt(common_arg( add_opt(common_arg(
{"--context-shift"}, {"--context-shift"},
string_format("enables context shift on infinite text generation (default: %s)", params.ctx_shift ? "disabled" : "enabled"), string_format("enables context shift on infinite text generation (default: %s)", params.ctx_shift ? "enabled" : "disabled"),
[](common_params & params) { [](common_params & params) {
params.ctx_shift = true; params.ctx_shift = true;
} }

2
common/common.h
View file

@ -375,7 +375,7 @@ struct common_params {
bool cont_batching = true; // insert new sequences for decoding on-the-fly bool cont_batching = true; // insert new sequences for decoding on-the-fly
bool flash_attn = false; // flash attention bool flash_attn = false; // flash attention
bool no_perf = false; // disable performance metrics bool no_perf = false; // disable performance metrics
bool ctx_shift = false; // context shift on inifinite text generation bool ctx_shift = false; // context shift on infinite text generation
bool swa_full = false; // use full-size SWA cache (https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055) bool swa_full = false; // use full-size SWA cache (https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055)
bool kv_unified = false; // enable unified KV cache bool kv_unified = false; // enable unified KV cache