yyj d1a3ed8a30 [perf]: add K2 RAWINT4 prefill mat-mat dispatch (#2080) ...

* [perf]: add K2 RAWINT4 prefill mat-mat dispatch

* [perf] Refactor K2 RAWINT4 prefill accumulation

---------

Co-authored-by: yyj6666667 <yyj6666667@users.noreply.github.com>

2026-07-19 21:43:01 +08:00

..

__init__.py

Kt minimax (#1742)

2025-12-24 15:39:44 +08:00

amx.py

[perf]: add K2 RAWINT4 prefill mat-mat dispatch (#2080)

2026-07-19 21:43:01 +08:00

llamafile.py

[fix]: fix --numa-nodes handling (#1904)

2026-03-31 17:50:22 +08:00

loader.py

fix: normalize compressed RAWINT4 weights (#2075)

2026-07-06 18:06:52 +08:00

moe_kernel.py

[fix]: fix --numa-nodes handling (#1904)

2026-03-31 17:50:22 +08:00