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
docs/decode-guide
FreeToken/tests/engine
T
History
ZihaoMuandLZ-QWQ 9cacd0896c fix(moe): publish rocm cpu expert inputs before notification (#764)
* fix(moe): prevent stale cpu expert inputs in rocm graphs

* fix(moe): publish rocm cpu inputs with graph events

* fix(moe): qualify rocm kernel io with ordered copy fallback

* fix(moe): enable locked hybrid staging on rocm

---------

Co-authored-by: LZ-QWQ <lz1830837889@163.com>
2026-11-02 21:29:42 -08:00
..
__init__.py
feat: initial open-source release
2026-08-11 22:53:25 +00:00
test_attention_backend_arch.py
fix(rocm): gate CUDA-only optional backends on ROCm (#134)
2026-10-08 19:55:57 -07:00
test_attention_backend_matrix.py
feat(rotary): size the rope table for YaRN and add --hf-overrides (#573)
2026-10-01 00:40:27 -07:00
test_cache_budget.py
refactor: add engine and scheduler seams for multi-row decode steps (#833)
2026-10-27 16:03:01 -07:00
test_mm_encoder.py
feat(mm): serve image input on the Qwen families (#454)
2026-09-13 15:39:33 -07:00
test_mm_repeated_image.py
feat(mm): serve image input on the Qwen families (#454)
2026-09-13 15:39:33 -07:00
test_moe_cpu_layers.py
fix(moe): publish rocm cpu expert inputs before notification (#764)
2026-11-02 21:29:42 -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