Skip to content

Commit 582dcfc

Browse files
Update README.md
Updated to-do list. Signed-off-by: Brad Hutchings <[email protected]>
1 parent 74293b6 commit 582dcfc

File tree

1 file changed

+3
-1
lines changed

1 file changed

+3
-1
lines changed

README.md

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -70,6 +70,8 @@ In no particular order of importance, these are the things that bother me:
7070
- GPU support without a complicated kludge, and that can support all supported platform / CPU / GPU triads. Perhaps a plugin system with shared library dispatch? Invoking dev tools on Apple Metal like llamafile does is "complicated".
7171
- Code signing instructions. Might have to sign executables within the zip package, plus the package itself.
7272
- Clean up remaining build warnings, either by fixing source (i.e. Cosmo) or finding the magical compiler flags.
73-
- Copy the `cosmo_args` function into `server.cpp` so it could potentially be incorporated upstream in non-Cosmo builds. `common/arg2.cpp` might be a good landing spot. License in [Cosmo source code](https://github.com/jart/cosmopolitan/blob/master/tool/args/args2.c) appears to be MIT compatible with attribution.
73+
- Copy the `cosmo_args` function into `server.cpp` so it could potentially be incorporated upstream in non-Cosmo builds. `common/arg2.cpp` might be a good landing spot. License in [Cosmo source code](https://github.com/jart/cosmopolitan/blob/master/tool/args/args2.c) appears to be MIT compatible with attribution.
74+
- The args thing is cute, but it might be easier as a yaml file. Key value pairs. Flags can be keys with null values.
7475
- The `--ctx-size` parameter doesn't seem quite right given that new models have the training (or max) context size in their metadata. That size should be used subject to a maximum in a passed parameter. E.g. So a 128K model can run comfortably on a smaller device.
7576
- Write docs for a Deploying step. It should address the args file, removing the extra executable depending on platform, models, host, port. context size.
77+
- Make a '.gitattributes' file so we can set the default file to be displayed and keep the README.md from llama.cpp. This will help in syncing changes continually from upstream. Reference: https://git-scm.com/docs/gitattributes

0 commit comments

Comments
 (0)