* Add common grammars and json-schema-to-grammar utility function from llama.cpp
* Pass functions to format function
* Add basic functionary formatting
* Add LlamaChatHandler for more complex chat use cases
* Add function calling example notebook
* Add support for regular chat completions alongside function calling
* Add low-level batching notebook
* fix: tokenization of special characters: (#850)
It should behave like llama.cpp, where most out of the box usages
treat special characters accordingly
* Update CHANGELOG
* Cleanup
* Fix runner label
* Update notebook
* Use llama_decode and batch api
* Support logits_all parameter
---------
Co-authored-by: Antoine Lizee <antoine.lizee@gmail.com>
This commit "deprecates" the example fastapi server by remaining runnable but pointing folks at the module if they want to learn more.
Rationale:
Currently there exist two server implementations in this repo:
- `llama_cpp/server/__main__.py`, the module that's runnable by consumers of the library with `python3 -m llama_cpp.server`
- `examples/high_level_api/fastapi_server.py`, which is probably a copy-pasted example by folks hacking around
IMO this is confusing. As a new user of the library I see they've both been updated relatively recently but looking side-by-side there's a diff.
The one in the module seems better:
- supports logits_all
- supports use_mmap
- has experimental cache support (with some mutex thing going on)
- some stuff with streaming support was moved around more recently than fastapi_server.py
Change batch size to the llama.cpp default of 8. I've seen issues in llama.cpp where batch size affects quality of generations. (It shouldn't) But in case that's still an issue I changed to default.
Set auto-determined num of threads to 1/2 system count. ggml will sometimes lock cores at 100% while doing nothing. This is being addressed, but can cause bad experience for user if pegged at 100%
