GitLab

Add Local Chat Test for CI/CD

fix flash_attn whl path in install job

use compile for gate, slight performance improvement

fix-singleton

cpuinfer: filter repeated backend instantiation

Update install.md

this  is a issue in your install tutorial

fix #829: support older AVX512-capable CPUs

[fix] thread context bug

release 0.2.3.post1

fix flashinfer precision

[fix] support openai chat completion api

Develop 0.2.3 ready to release

🚑 Merge branch 'develop-0.2.3' of https://github.com/kvcache-ai/ktransformers into develop-0.2.3

[fix] fix gcc compilation

fix: list models API

Fix the list models API to match the corresponding OpenAI API format.

V0.2.3

⚡ release v0.2.3

Update install.md