Merge branch 'kvcache-ai:main' into main

877aec85 · Yuhao Tsui · GitHub · 84164f58 · 9037bf30 · 877aec85
Unverified Commit 877aec85 authored Apr 09, 2025 by Yuhao Tsui Committed by GitHub Apr 09, 2025
20 changed files
--- a/ktransformers/ktransformers_ext/cuda/gptq_marlin/gptq_marlin.cu
+++ b/ktransformers/ktransformers_ext/cuda/gptq_marlin/gptq_marlin.cu
--- a/ktransformers/ktransformers_ext/cuda/gptq_marlin/gptq_marlin.cuh
+++ b/ktransformers/ktransformers_ext/cuda/gptq_marlin/gptq_marlin.cuh
--- a/ktransformers/ktransformers_ext/cuda/gptq_marlin/gptq_marlin_dtypes.cuh
+++ b/ktransformers/ktransformers_ext/cuda/gptq_marlin/gptq_marlin_dtypes.cuh
--- a/ktransformers/ktransformers_ext/cuda/gptq_marlin/ops.h
+++ b/ktransformers/ktransformers_ext/cuda/gptq_marlin/ops.h
--- a/ktransformers/ktransformers_ext/cuda/setup.py
+++ b/ktransformers/ktransformers_ext/cuda/setup.py
--- a/ktransformers/ktransformers_ext/cuda/test_dequant.py
+++ b/ktransformers/ktransformers_ext/cuda/test_dequant.py
--- a/ktransformers/ktransformers_ext/examples/test_attention.py
+++ b/ktransformers/ktransformers_ext/examples/test_attention.py
--- a/ktransformers/ktransformers_ext/examples/test_linear.py
+++ b/ktransformers/ktransformers_ext/examples/test_linear.py
--- a/ktransformers/ktransformers_ext/examples/test_mlp.py
+++ b/ktransformers/ktransformers_ext/examples/test_mlp.py
--- a/ktransformers/ktransformers_ext/examples/test_moe.py
+++ b/ktransformers/ktransformers_ext/examples/test_moe.py
--- a/ktransformers/ktransformers_ext/ext_bindings.cpp
+++ b/ktransformers/ktransformers_ext/ext_bindings.cpp
--- a/ktransformers/ktransformers_ext/operators/kvcache/kvcache.h
+++ b/ktransformers/ktransformers_ext/operators/kvcache/kvcache.h
--- a/ktransformers/ktransformers_ext/operators/kvcache/kvcache_attn.cpp
+++ b/ktransformers/ktransformers_ext/operators/kvcache/kvcache_attn.cpp
--- a/ktransformers/ktransformers_ext/operators/kvcache/kvcache_load_dump.cpp
+++ b/ktransformers/ktransformers_ext/operators/kvcache/kvcache_load_dump.cpp
--- a/ktransformers/ktransformers_ext/operators/kvcache/kvcache_read_write.cpp
+++ b/ktransformers/ktransformers_ext/operators/kvcache/kvcache_read_write.cpp
--- a/ktransformers/ktransformers_ext/operators/kvcache/kvcache_utils.cpp
+++ b/ktransformers/ktransformers_ext/operators/kvcache/kvcache_utils.cpp
--- a/ktransformers/ktransformers_ext/operators/llamafile/conversion.h
+++ b/ktransformers/ktransformers_ext/operators/llamafile/conversion.h
--- a/ktransformers/ktransformers_ext/operators/llamafile/linear.cpp
+++ b/ktransformers/ktransformers_ext/operators/llamafile/linear.cpp
--- a/ktransformers/ktransformers_ext/operators/llamafile/linear.h
+++ b/ktransformers/ktransformers_ext/operators/llamafile/linear.h
--- a/ktransformers/ktransformers_ext/operators/llamafile/mlp.cpp
+++ b/ktransformers/ktransformers_ext/operators/llamafile/mlp.cpp