ktransformers

mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-19 22:09:10 +00:00

Files

ErvinXie 71f683acec Support Native Kimi K2 Thinking (#1663 )

* [feat]: fix k2 prefill

* Update Kimi-K2-Thinking.md

* Create Kimi-K2-Thinking-Native.md

* Update Kimi-K2-Thinking.md

* Update Kimi-K2-Thinking.md

* Update Kimi-K2-Thinking-Native.md

* [perf] optimize K2 MoE weight loading with per-expert pointers

- Avoid expensive torch.stack().contiguous() in Python (was ~6.6s)
- Use per-expert pointer arrays (gate_projs) instead of contiguous memory
- C++ worker pool performs parallel memcpy for TP slicing
- Add LOAD_TIME_PROFILE for load_weights timing analysis

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: ouqingliang <1692110604@qq.com>
Co-authored-by: Claude <noreply@anthropic.com>

2025-12-05 21:53:05 +08:00

amx

Support Native Kimi K2 Thinking (#1663 )

2025-12-05 21:53:05 +08:00

kvcache

update kt-kernel

2025-11-03 15:19:52 +08:00

llamafile

[feat](moe_kernel): add amd blis support (int8) (#1600 )

2025-11-27 12:08:53 +08:00

moe_kernel

[feat](moe_kernel): add amd blis support (int8) (#1600 )