T Git
首页 开源 帮助 登录 注册
trending/FreeToken
Watch 1
Star 0
Fork 0
mirror of https://github.com/FlashML-org/FreeToken.git synced 2026-11-21 01:52:30 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
main
FreeToken/python/freetoken/kernel/csrc/ggml
T
History
Xiaoze Fan ef6b303304 fix(ggml): cap the MoE route sort's shared memory at the device limit (#878)
2026-11-07 23:30:06 -08:00
..
freetoken
fix(moe): skip inactive gguf routes in hybrid decode (#823)
2026-10-28 22:28:13 -07:00
ggml-cpu
feat(cpu-moe): serve GGUF experts on the cpu and hybrid backends through ggml-cpu (#704)
2026-10-16 22:28:34 -07:00
ggml-cuda
fix(ggml): cap the MoE route sort's shared memory at the device limit (#878)
2026-11-07 23:30:06 -08:00
include
feat(cpu-moe): serve GGUF experts on the cpu and hybrid backends through ggml-cpu (#704)
2026-10-16 22:28:34 -07:00
src
feat(cpu-moe): serve GGUF experts on the cpu and hybrid backends through ggml-cpu (#704)
2026-10-16 22:28:34 -07:00
LICENSE
feat(gguf): serve GGUF checkpoints on vendored ggml-cuda kernels (#690)
2026-10-15 16:33:16 -07:00
VERSION
chore(ggml): replace freetoken.patch with the llama.cpp pin (#873)
2026-11-05 15:13:56 -08:00
📖 帮助文档 · 📡 API · 🔍 开源资源 · 🌐 koklan.biz
T Git · AI 时代的代码协作平台 · © 海南科凯联科技有限公司 · 琼ICP备2025050379号-3