-
Notifications
You must be signed in to change notification settings - Fork 27
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
Showing
1 changed file
with
1 addition
and
1 deletion.
There are no files selected for viewing
Submodule llama_cpp
updated
33 files
+7 −3 | .github/workflows/build.yml | |
+12 −1 | CMakeLists.txt | |
+29 −0 | Makefile | |
+1 −1 | ci/run.sh | |
+4 −3 | common/common.cpp | |
+2 −5 | common/sampling.cpp | |
+1 −1 | examples/batched-bench/batched-bench.cpp | |
+1 −1 | examples/batched/batched.cpp | |
+19 −19 | examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp | |
+0 −2 | examples/export-lora/export-lora.cpp | |
+1 −1 | examples/llava/README.md | |
+1 −5 | examples/llava/llava-surgery.py | |
+1 −1 | examples/perplexity/perplexity.cpp | |
+4 −2 | examples/quantize/quantize.cpp | |
+66 −0 | examples/server/README.md | |
+97 −4 | examples/server/server.cpp | |
+17 −3 | examples/server/utils.hpp | |
+7 −7 | examples/train-text-from-scratch/train-text-from-scratch.cpp | |
+3 −3 | flake.lock | |
+3 −3 | ggml-alloc.c | |
+10 −9 | ggml-backend.c | |
+278 −203 | ggml-cuda.cu | |
+55 −11 | ggml-metal.m | |
+378 −6 | ggml-metal.metal | |
+627 −30 | ggml-quants.c | |
+12 −2 | ggml-quants.h | |
+129 −50 | ggml.c | |
+11 −4 | ggml.h | |
+99 −50 | llama.cpp | |
+1 −0 | llama.h | |
+37 −39 | tests/test-backend-ops.cpp | |
+10 −10 | tests/test-grammar-parser.cpp | |
+2 −2 | tests/test-llama-grammar.cpp |