vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update README.md

Browse source
This commit is contained in:
pudepiedj 2024-02-23 10:01:24 +00:00 • committed by GitHub
parent 9aa1457066
commit 62ef858d00
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/server/README.md
View file

@ -41,8 +41,8 @@ see https://github.com/ggerganov/llama.cpp/issues/1437
- `-cb`, `--cont-batching`: enable continuous batching (a.k.a dynamic batching) (default: disabled)
- `-spf FNAME`, `--system-prompt-file FNAME` Set a file to load "a system prompt (initial prompt of all slots), this is useful for chat applications. [See more](#change-system-prompt-on-runtime)
- `--mmproj MMPROJ_FILE`: Path to a multimodal projector file for LLaVA.
- '-skvg' or '--show-graphics': display a dynamic graphic of kvcache occupancy per slot.
- '-skvi' or '--show-interactive-graphics': display a dynamic graphic of kvcache that requires user intervention to move on after each request
- `-skvg` or `--show-graphics`: display a dynamic graphic of kvcache occupancy per slot.
- `-skvi` or `--show-interactive-graphics`: display a dynamic graphic of kvcache that requires user intervention to move on after each request
- `--grp-attn-n`: Set the group attention factor to extend context size through self-extend(default: 1=disabled), used together with group attention width `--grp-attn-w`
- `--grp-attn-w`: Set the group attention width to extend context size through self-extend(default: 512), used together with group attention factor `--grp-attn-n`
- `-n, --n-predict`: Set the maximum tokens to predict (default: -1)