Gentoo Packages

sci-ml/colibri (bennypowers)

Search

Install

Install this package:

emerge -a sci-ml/colibri

Package Information

Description:
Colibri runs GLM-5.2 (744B-parameter MoE) on consumer hardware with as little as 25GB RAM. Pure C engine with zero runtime dependencies, streaming experts from disk with an LRU cache. Supports MLA attention, MTP speculative decoding, and optional CUDA GPU offloading.
Homepage:
https://github.com/JustVugg/colibri
License:
Apache-2.0

Versions

Version EAPI Keywords Slot
9999 8 0
1.7.0 8 ~amd64 0
1.5.0 8 ~amd64 0
1.4.0 8 ~amd64 0
1.11.0 8 ~amd64 0
1.10.2 8 ~amd64 0
1.10.1 8 ~amd64 0
1.10.0 8 ~amd64 0
1.10.0 8 ~amd64 0
1.1.1 8 ~amd64 0
1.1.0 8 ~amd64 0
1.1.0 8 ~amd64 0

Metadata

Description

Maintainers

Upstream

Raw Metadata XML 
<pkgmetadata>
	<maintainer type="person">
		<email>web@bennypowers.com</email>
		<name>Benny Powers</name>
	</maintainer>
	<longdescription lang="en">
		Colibri runs GLM-5.2 (744B-parameter MoE) on consumer hardware with
		as little as 25GB RAM. Pure C engine with zero runtime dependencies,
		streaming experts from disk with an LRU cache. Supports MLA attention,
		MTP speculative decoding, and optional CUDA GPU offloading.
	</longdescription>
	<use>
		<flag name="bench">Install dependencies for quality benchmarks
			(MMLU, HellaSwag, ARC)</flag>
		<flag name="cuda">Build with NVIDIA CUDA GPU offloading for
			resident expert tensors</flag>
		<flag name="python">Install the coli Python CLI for model management,
			chat, serving, and weight conversion</flag>
		<flag name="rocm">Build with AMD ROCm/HIP GPU offloading for
			resident expert tensors</flag>
	</use>
	<upstream>
		<remote-id type="github">JustVugg/colibri</remote-id>
	</upstream>
</pkgmetadata>

Lint Warnings

USE Flags

Manage flags for this package: euse -i <flag> -p sci-ml/colibri | euse -E <flag> -p sci-ml/colibri | euse -D <flag> -p sci-ml/colibri

Flag Description 9999 1.7.0 1.5.0 1.4.0 1.11.0 1.10.2 1.10.1 1.10.0 1.10.0 1.1.1 1.1.0 1.1.0
bench Install dependencies for quality benchmarks (MMLU, HellaSwag, ARC) ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓
cuda Build with NVIDIA CUDA GPU offloading for resident expert tensors ✗ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓
python Install the coli Python CLI for model management, chat, serving, and weight conversion ⊕ ⊕ ⊕ ⊕ ⊕ ⊕ ⊕ ⊕ ⊕ ⊕ ⊕ ⊕
rocm Build with AMD ROCm/HIP GPU offloading for resident expert tensors ✗ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓

Manifest

Type File Size Versions
DIST colibri-1.1.0.tar.gz 3344699 bytes 1.1.0
DIST colibri-1.1.1.tar.gz 3362669 bytes 1.1.1
DIST colibri-1.10.0.tar.gz 5914029 bytes 1.10.0
DIST colibri-1.10.1.tar.gz 5923136 bytes 1.10.1
DIST colibri-1.10.2.tar.gz 5978095 bytes 1.10.2
DIST colibri-1.11.0.tar.gz 6208961 bytes 1.11.0
DIST colibri-1.4.0.tar.gz 4316051 bytes 1.4.0
DIST colibri-1.5.0.tar.gz 4653121 bytes 1.5.0
DIST colibri-1.7.0.tar.gz 5228514 bytes 1.7.0
Unmatched Entries
Type File Size