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
fix/modelopt-mixed-method
FreeToken/python/freetoken/layers/quantization/moe
T
History
Xiaoze Fan 33cbb3c54e feat(utils): add once-per-message logger methods (#858)
debug_once / info_once / warning_once log on rank 0, once per distinct message and args. select_kernel, which logged its choice once per layer, and the hand-rolled log-once guards now use them.
2026-11-03 15:31:08 -08:00
..
__init__.py
feat(gguf): serve GGUF checkpoints on vendored ggml-cuda kernels (#690)
2026-10-15 16:33:16 -07:00
base.py
feat(gguf): serve gpt-oss gguf checkpoints on gpt_oss (#838)
2026-11-02 08:58:07 -08:00
fp8_block.py
perf(moe): skip inactive block-fp8 decode routes (#665)
2026-10-22 15:43:34 -07:00
gguf.py
feat(gguf): serve gpt-oss gguf checkpoints on gpt_oss (#838)
2026-11-02 08:58:07 -08:00
mxfp4.py
feat(moe): serve experts of several formats through per-format slot pools (#700)
2026-10-16 15:13:59 -07:00
mxfp8.py
refactor(quant): config, scheme and method layers for quantization (#418)
2026-09-08 23:37:23 -07:00
nvfp4.py
feat(utils): add once-per-message logger methods (#858)
2026-11-03 15:31:08 -08:00
unquantized.py
feat(moe): serve NVFP4 and MXFP4 experts fused through the expert banks (#601)
2026-10-04 13:51:55 -07:00
📖 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