CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : disable context shift by default (#15416)

Browse Source 
* server : disable context shift by default

ggml-ci

* server : make scopr of test parameters local
This commit is contained in:
Georgi Gerganov
2025-08-19 16:46:37 +03:00
committed by GitHub
parent a6d3cfe7fa
commit d2fcd91cf9
16 changed files with 27 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
common/arg.cpp
View File

@@ -1530,6 +1530,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.ctx_shift = false;
}
).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(
{"--context-shift"},
string_format("enables context shift on infinite text generation (default: %s)", params.ctx_shift ? "disabled" : "enabled"),
[](common_params & params) {
params.ctx_shift = true;
}
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_PERPLEXITY}).set_env("LLAMA_ARG_CONTEXT_SHIFT"));
add_opt(common_arg(
{"--chunks"}, "N",
string_format("max number of chunks to process (default: %d, -1 = all)", params.n_chunks),

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 flash_attn = false; // flash attention
bool no_perf = false; // disable performance metrics
bool ctx_shift = true; // context shift on inifinite text generation
bool ctx_shift = false; // context shift on inifinite text generation
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