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
T
History
Xiaoze Fan 42553c5463 fix(quant): accept the modelopt_mixed quant method
2026-11-09 19:24:14 +00:00
..
linear_attn
feat(spec): verify draft tokens on the target side (#836)
2026-10-28 21:18:02 -07:00
quantization
fix(quant): accept the modelopt_mixed quant method
2026-11-09 19:24:14 +00:00
__init__.py
feat: add --embed-weights host for a pinned host embedding table (#806)
2026-10-23 14:41:37 -07:00
activation.py
feat(gguf): serve GGUF checkpoints on vendored ggml-cuda kernels (#690)
2026-10-15 16:33:16 -07:00
base.py
feat: add --embed-weights host for a pinned host embedding table (#806)
2026-10-23 14:41:37 -07:00
embedding.py
feat(spec): add DFlash 2 speculative decoding (#857)
2026-11-07 12:29:18 -08:00
linear.py
feat(gguf): serve GGUF checkpoints on vendored ggml-cuda kernels (#690)
2026-10-15 16:33:16 -07:00
mhc.py
feat(deepseek-v41): support text and vision serving (#603)
2026-10-07 00:15:11 -07:00
moe.py
feat(gguf): serve GGUF checkpoints on vendored ggml-cuda kernels (#690)
2026-10-15 16:33:16 -07:00
norm.py
feat(gemma4): serve image input on the Gemma-4 releases (#467)
2026-09-14 13:04:33 -07:00
rotary.py
fix(rotary): preserve fp32 inputs in mrope torch fallbacks (#641)
2026-10-23 00:11:06 -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