Huang Wensen 6d460cc107 [feat](kt-kernel): packed-int4-resident AVX-VNNI-256 GPTQ INT4 backend (#2187)

2026-09-07 20:20:04 +08:00

..

cli

Add MiniMax-M3 and MiniMax-M2.7 to the kt-cli model registry (#2112)

2026-08-21 17:53:58 +08:00

sft

perf(sft): defer backward repack wait to CPU consumer (#2188)

2026-09-07 17:39:26 +08:00

utils

[feat](kt-kernel): packed-int4-resident AVX-VNNI-256 GPTQ INT4 backend (#2187)

2026-09-07 20:20:04 +08:00

__init__.py

[feat](kt-sft): Activation reuse & Int8 kernel refactor & native block-FP8 LoRA SFT (#2141)

2026-08-17 16:25:14 +08:00

_cpu_detect.py

[feat](kt-sft): Activation reuse & Int8 kernel refactor & native block-FP8 LoRA SFT (#2141)

2026-08-17 16:25:14 +08:00

experts_base.py

[feat](kt-kernel): Ascend NPU backend for single-card DeepSeek-V4-Flash offload (#2157)

2026-09-01 20:10:24 +08:00

experts.py

[feat](kt-kernel): Ascend NPU backend for single-card DeepSeek-V4-Flash offload (#2157)

2026-09-01 20:10:24 +08:00