kytensor-llm 1.0.0-ok0.6 source package in openKylin

Changelog

kytensor-llm (1.0.0-ok0.6) unstable; urgency=medium

  * Add loongarch and riscv64 arch build support
  * Support Qwen3 and Qwen3MoE
  * Add SSE 4.2

 -- liuyihu <email address hidden>  Fri, 12 Sep 2025 16:52:40 +0800

Upload details

Uploaded by:
liuyihu
Sponsored by:
Cibot
Uploaded to:
Nile.bedrock
Original maintainer:
Kylin Developers
Architectures:
any
Section:
libdevel
Urgency:
Medium Urgency

Publishing See full publishing history

Series Pocket Published Component Section
Nile.bedrock proposed main libdevel

Downloads

File Size SHA-256 Checksum
kytensor-llm_1.0.0-ok0.6.tar.xz 14.3 MiB 0fe08b772e9a1e1d95e6c20d10f19992f9bc181ea2ff8d26aa2013d936b759a4
kytensor-llm_1.0.0-ok0.6.dsc 1.4 KiB 4eacad3f7f07a868185762bb85e1e18448be64b1da4a2ae198b9d619aad643aa

Available diffs

View changes file

Binary packages built by this source

kytensor-llm: Inference of Meta's LLaMA model (and others) in pure C/C++

 This package contains the llama.cpp core runtime libraries.
 The main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art performance on a wide variety of hardware - locally and in the cloud.

kytensor-llm-dbgsym: debug symbols for kytensor-llm
kytensor-llm-dev: development files for llama.cpp

 This package contains the header files to compile applications that use llama.cpp, and contains the binary files to run llama.cpp.
 The main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art performance on a wide variety of hardware - locally and in the cloud.

kytensor-llm-dev-dbgsym: debug symbols for kytensor-llm-dev