-
Notifications
You must be signed in to change notification settings - Fork 56
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Marcus Dunn
committed
Mar 5, 2024
1 parent
bda46e1
commit 566ad3c
Showing
1 changed file
with
1 addition
and
1 deletion.
There are no files selected for viewing
Submodule llama.cpp
updated
29 files
+1 −0 | README.md | |
+6 −1 | common/CMakeLists.txt | |
+1 −8 | common/common.cpp | |
+2 −3 | common/common.h | |
+79 −0 | common/sampling.cpp | |
+7 −0 | common/sampling.h | |
+3 −0 | convert-hf-to-gguf.py | |
+21 −7 | examples/embedding/embedding.cpp | |
+20 −0 | examples/main/main.cpp | |
+34 −0 | examples/server-embd.py | |
+43 −12 | examples/server/server.cpp | |
+1 −0 | examples/speculative/README.md | |
+168 −48 | examples/speculative/speculative.cpp | |
+4 −3 | ggml-backend-impl.h | |
+18 −21 | ggml-backend.c | |
+16 −15 | ggml-backend.h | |
+189 −44 | ggml-cuda.cu | |
+2 −2 | ggml-kompute.cpp | |
+63 −7 | ggml-metal.m | |
+43 −0 | ggml-metal.metal | |
+2 −2 | ggml-opencl.cpp | |
+2 −2 | ggml-sycl.cpp | |
+2 −2 | ggml-vulkan.cpp | |
+223 −14 | ggml.c | |
+30 −4 | ggml.h | |
+253 −114 | llama.cpp | |
+12 −6 | llama.h | |
+1 −1 | scripts/sync-ggml.last | |
+46 −0 | tests/test-backend-ops.cpp |