Olivier Chafik
@ochafik.bsky.social
OpenSCAD & llama.cpp contributor.
Used to dream in Scala, now waiting for a reason to learn Rust.
ex-Googler (views expressed = my own)
he/him 🏳️🌈
Also found at: @ochafik@fosstodon.org
(Slowly moving out of https://x.com/ochafik)
Used to dream in Scala, now waiting for a reason to learn Rust.
ex-Googler (views expressed = my own)
he/him 🏳️🌈
Also found at: @ochafik@fosstodon.org
(Slowly moving out of https://x.com/ochafik)
llama.cpp streaming support for tool calling & thoughts was just merged: please test & report any issues 😅
github.com/ggml-org/lla...
#llamacpp
github.com/ggml-org/lla...
#llamacpp
`server`: streaming of tool calls and thoughts when `--jinja` is on by ochafik · Pull Request #12379 · ggml-org/llama.cpp
This PR is still WIP (see todos at the bottom) but welcoming early feedback / testing
Support streaming of tool calls in OpenAI format
Improve handling of thinking model (DeepSeek R1 Distills, QwQ...
github.com
May 25, 2025 at 11:25 AM
llama.cpp streaming support for tool calling & thoughts was just merged: please test & report any issues 😅
github.com/ggml-org/lla...
#llamacpp
github.com/ggml-org/lla...
#llamacpp
Llama.cpp now supports tool calling (OpenAI-compatible)
github.com/ggerganov/ll...
On top of generic support for *all* models, it supports 8+ models’ native formats:
- Llama 3.x
- Functionary 3
- Hermes 2/3
- Qwen 2.5
- Mistral Nemo
- Firefunction 3
- DeepSeek R1
🧵 #llamacpp
github.com/ggerganov/ll...
On top of generic support for *all* models, it supports 8+ models’ native formats:
- Llama 3.x
- Functionary 3
- Hermes 2/3
- Qwen 2.5
- Mistral Nemo
- Firefunction 3
- DeepSeek R1
🧵 #llamacpp
Tool call support (generic + native for Llama, Functionary, Hermes, Mistral, Firefunction, DeepSeek) w/ lazy grammars by ochafik · Pull Request #9639 · ggerganov/llama.cpp
This supersedes #6389 (now using a fully C++ approach), #5695 (first attempt at supporting Functionary) and #9592 (more recent Python wrapper).
Which models are supported (in their native style)?
W...
github.com
February 1, 2025 at 1:45 PM
Llama.cpp now supports tool calling (OpenAI-compatible)
github.com/ggerganov/ll...
On top of generic support for *all* models, it supports 8+ models’ native formats:
- Llama 3.x
- Functionary 3
- Hermes 2/3
- Qwen 2.5
- Mistral Nemo
- Firefunction 3
- DeepSeek R1
🧵 #llamacpp
github.com/ggerganov/ll...
On top of generic support for *all* models, it supports 8+ models’ native formats:
- Llama 3.x
- Functionary 3
- Hermes 2/3
- Qwen 2.5
- Mistral Nemo
- Firefunction 3
- DeepSeek R1
🧵 #llamacpp
Universal llama.cpp tool call is coming: I've just released Minja, a minimalistic Jinja template engine reimplementation in C++ for LLM chat templates:
github.com/google/minja
(*not an official Google product*)
#LLM #AI #EdgeAI #OSS
🧵 1/4
github.com/google/minja
(*not an official Google product*)
#LLM #AI #EdgeAI #OSS
🧵 1/4
GitHub - google/minja: A minimalistic C++ Jinja templating engine for LLM chat templates
A minimalistic C++ Jinja templating engine for LLM chat templates - google/minja
github.com
December 4, 2024 at 4:40 PM
Universal llama.cpp tool call is coming: I've just released Minja, a minimalistic Jinja template engine reimplementation in C++ for LLM chat templates:
github.com/google/minja
(*not an official Google product*)
#LLM #AI #EdgeAI #OSS
🧵 1/4
github.com/google/minja
(*not an official Google product*)
#LLM #AI #EdgeAI #OSS
🧵 1/4
Reposted by Olivier Chafik
#Manifold v3.0 is out! This is a huge release - we have removed *all* required dependencies.
Our npm package is half the size and twice the speed. Our #SDF LevelSet is much faster and higher quality.
And so much more: github.com/elalish/mani...
Our npm package is half the size and twice the speed. Our #SDF LevelSet is much faster and higher quality.
And so much more: github.com/elalish/mani...
November 18, 2024 at 6:58 PM
#Manifold v3.0 is out! This is a huge release - we have removed *all* required dependencies.
Our npm package is half the size and twice the speed. Our #SDF LevelSet is much faster and higher quality.
And so much more: github.com/elalish/mani...
Our npm package is half the size and twice the speed. Our #SDF LevelSet is much faster and higher quality.
And so much more: github.com/elalish/mani...