update

768ab4df · xuxzh1 · 44f79c7e · 768ab4df · 768ab4df · 768ab4df
Commit 768ab4df authored Nov 13, 2024 by xuxzh1 🎱
20 changed files
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_0.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_0.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_1.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_1.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_0.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_0.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_1.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_1.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q8_0.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q8_0.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb16.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb16.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb32.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb32.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb16.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb16.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb32.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb32.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb8.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb8.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/generate_cu_files.py
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/generate_cu_files.py
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq1_s.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq1_s.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_s.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_s.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xs.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xs.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xxs.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xxs.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_s.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_s.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_xxs.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_xxs.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu
--- a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu
+++ b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu