From 3f0bab3a3b9b420210d607341998054726ba9751 Mon Sep 17 00:00:00 2001 From: Concedo <39025047+LostRuins@users.noreply.github.com> Date: Fri, 10 Jul 2026 15:18:17 +0800 Subject: [PATCH] fixed default gen amt not actually increased (+1 squashed commits) Squashed commits: [8e2417d83] fixed default gen amt not actually increased --- koboldcpp.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/koboldcpp.py b/koboldcpp.py index 68d2d2857..2c9862e1c 100644 --- a/koboldcpp.py +++ b/koboldcpp.py @@ -78,7 +78,7 @@ dry_seq_break_max = 128 extra_images_max = 4 # for kontext/qwen img # global vars -KcppVersion = "1.117" +KcppVersion = "1.117.1" showdebug = True kcpp_instance = None #global running instance global_memory = {"tunnel_url": "", "restart_target":"", "input_to_exit":False, "load_complete":False, "restart_override_base_config":"", "last_active_timestamp":datetime.now(), "triggered_sleeping":False, "current_model":"initial_model", "base_config":"", "swapReqType": None, "autoswapmode": False} @@ -12362,7 +12362,7 @@ if __name__ == '__main__': advparser.add_argument("--chatcompletionsadapter", metavar=('[filename]'), help="Select an optional ChatCompletions Adapter JSON file to force custom instruct tags.", default="AutoGuess") advparser.add_argument("--cli", help="Does not launch KoboldCpp HTTP server. Instead, enables KoboldCpp from the command line, accepting interactive console input and displaying responses to the terminal.", action='store_true') advparser.add_argument("--debugmode", help="Shows additional debug info in the terminal. Levels: -1 (Horde-quiet, suppresses non-essential prints; auto-applied when Horde args are set), 0 (default, normal output), 1 (verbose: extra slot/cache info, larger print buffers, retains horde-debug prefix). Passing the flag without a value implies 1.", nargs='?', const=1, type=int, default=0) - advparser.add_argument("--defaultgenamt", help="How many tokens to generate by default, if not specified. Must be smaller than context size. Usually, your frontend GUI will override this.", type=check_range(int,64,16384), default=default_genlen) + advparser.add_argument("--defaultgenamt", help="How many tokens to generate by default, if not specified. Must be smaller than context size. Usually, your frontend GUI will override this.", type=check_range(int,64,32768), default=default_genlen) advparser.add_argument("--device", "-dev", metavar=(''), help="Set llama.cpp compatible device selection override. Comma separated. Overrides normal device choices.", default="") advparser.add_argument("--downloaddir", metavar=('[directory]'), help="Specify a directory that models will be downloaded to or searched from, if unset uses the working directory.", default="") advparser.add_argument("--draftamount","--draft-max","--draft-n","--spec-draft-n-max", metavar=('[tokens]'), help="How many tokens to draft per chunk before verifying results", type=int, default=default_draft_amount)