llama-cpp-python

mirror of https://github.com/abetlen/llama-cpp-python.git synced 2026-03-27 05:33:00 +00:00

Files

Andrei 11e7a55af7 fix: Qwen 3.5 support (#2152 )

* fix: handle Qwen 3.5 hybrid prefix reuse

* test: fix Qwen runtime unit mocks

* test: drop Qwen runtime unit tests

* docs: credit Qwen fix contributors in changelog

* docs/tests: update default Qwen model to 3.5 0.8B

* test: rebaseline Qwen 3.5 outputs

* test: stabilize low-level Qwen sampling check

* test: tighten Qwen 3.5 completion prompts

2026-03-22 22:33:31 -07:00

build-and-release.yaml

ci: add riscv64 wheel builds to release workflow (#2139 )

2026-03-22 19:27:22 -07:00

build-docker.yaml

fix(ci): Update docker runner

2025-07-06 00:45:59 -04:00

build-wheels-cuda.yaml

fix(ci): Temporarily disable windows cuda wheels

2025-07-06 00:55:34 -04:00

build-wheels-metal.yaml

fix(ci): Remove macos-13 builds to fix cross compilation error