Skip to content

Commit

Permalink
Merge pull request #63 from utilityai/update-llama-cpp-2024-02-03
Browse files Browse the repository at this point in the history 
updated llama.cpp
  • Loading branch information
@MarcusDunn
MarcusDunn authored Feb 3, 2024
2 parents 3319ff3 + e7f1847 commit ee4eb35
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion llama-cpp-sys-2/llama.cpp
Submodule llama.cpp updated 23 files
+9 −7 .devops/main-intel.Dockerfile
+29 −0 .devops/main-vulkan.Dockerfile
+10 −7 .devops/server-intel.Dockerfile
+29 −0 .devops/server-vulkan.Dockerfile
+4 −1 Makefile
+119 −49 README-sycl.md
+49 −15 README.md
+153 −1 convert-hf-to-gguf.py
+21 −13 examples/llama-bench/README.md
+54 −6 examples/llama-bench/llama-bench.cpp
+2 −2 examples/perplexity/perplexity.cpp
+1 −1 examples/sycl/win-run-llama2.bat
+3 −3 ggml-cuda.cu
+78 −29 ggml-sycl.cpp
+2 −1 ggml-sycl.h
+69 −63 ggml-vulkan-shaders.hpp
+12 −5 ggml-vulkan.cpp
+2 −1 ggml_vk_generate_shaders.py
+18 −0 gguf-py/gguf/constants.py
+3 −0 gguf-py/gguf/gguf_writer.py
+12 −2 gguf-py/gguf/tensor_mapping.py
+213 −12 llama.cpp
+25 −1 scripts/server-llm.sh

0 comments on commit ee4eb35

Please sign in to comment.