Skip to content

Commit

Permalink
feat: sync llama.cpp
Browse files Browse the repository at this point in the history
  • Loading branch information
@jhen0409
jhen0409 committed Dec 31, 2024
1 parent 20b8751 commit 7d5c1ba
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion src/llama.cpp
Submodule llama.cpp updated 89 files
+81 −0 .devops/cpu.Dockerfile
+94 −0 .devops/cuda.Dockerfile
+0 −33 .devops/full-cuda.Dockerfile
+0 −33 .devops/full-musa.Dockerfile
+0 −50 .devops/full-rocm.Dockerfile
+0 −38 .devops/full.Dockerfile
+91 −0 .devops/intel.Dockerfile
+0 −38 .devops/llama-cli-cuda.Dockerfile
+0 −28 .devops/llama-cli-intel.Dockerfile
+0 −38 .devops/llama-cli-musa.Dockerfile
+0 −45 .devops/llama-cli-rocm.Dockerfile
+0 −27 .devops/llama-cli-vulkan.Dockerfile
+0 −29 .devops/llama-cli.Dockerfile
+0 −43 .devops/llama-server-cuda.Dockerfile
+0 −34 .devops/llama-server-intel.Dockerfile
+0 −43 .devops/llama-server-musa.Dockerfile
+0 −54 .devops/llama-server-rocm.Dockerfile
+0 −31 .devops/llama-server-vulkan.Dockerfile
+0 −33 .devops/llama-server.Dockerfile
+108 −0 .devops/musa.Dockerfile
+113 −0 .devops/rocm.Dockerfile
+88 −0 .devops/vulkan.Dockerfile
+76 −28 .github/workflows/docker.yml
+210 −1 convert_hf_to_gguf.py
+2 −0 convert_hf_to_gguf_update.py
+1 −1 examples/cvector-generator/mean.hpp
+1 −1 examples/cvector-generator/pca.hpp
+3 −3 examples/export-lora/export-lora.cpp
+3 −1 examples/llama.android/llama/src/main/cpp/llama-android.cpp
+12 −0 examples/rpc/rpc-server.cpp
+2 −0 examples/run/README.md
+73 −38 examples/run/run.cpp
+1 −0 examples/server/CMakeLists.txt
+4 −1 examples/server/README.md
+ − examples/server/public/index.html.gz
+38 −17 examples/server/server.cpp
+3 −0 examples/server/tests/unit/test_chat_completion.py
+38 −3 examples/server/tests/unit/test_completion.py
+41 −0 examples/server/tests/unit/test_embedding.py
+46 −6 examples/server/utils.hpp
+19 −4 examples/server/webui/src/main.js
+1 −0 ggml/src/CMakeLists.txt
+74 −49 ggml/src/ggml-backend-reg.cpp
+32 −21 ggml/src/ggml-cpu/CMakeLists.txt
+51 −71 ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp
+6 −6 ggml/src/ggml-cpu/ggml-cpu.c
+264 −258 ggml/src/ggml-cpu/llamafile/sgemm.cpp
+2 −2 ggml/src/ggml-cpu/llamafile/sgemm.h
+5 −3 ggml/src/ggml-sycl/common.cpp
+4 −0 ggml/src/ggml-sycl/common.hpp
+26 −20 ggml/src/ggml-sycl/ggml-sycl.cpp
+164 −92 ggml/src/ggml-vulkan/ggml-vulkan.cpp
+2 −2 ggml/src/ggml-vulkan/vulkan-shaders/acc.comp
+1 −1 ggml/src/ggml-vulkan/vulkan-shaders/add.comp
+2 −2 ggml/src/ggml-vulkan/vulkan-shaders/clamp.comp
+3 −3 ggml/src/ggml-vulkan/vulkan-shaders/concat.comp
+4 −4 ggml/src/ggml-vulkan/vulkan-shaders/contig_copy.comp
+2 −2 ggml/src/ggml-vulkan/vulkan-shaders/copy.comp
+2 −2 ggml/src/ggml-vulkan/vulkan-shaders/cos.comp
+45 −25 ggml/src/ggml-vulkan/vulkan-shaders/dequant_funcs_cm2.comp
+1 −1 ggml/src/ggml-vulkan/vulkan-shaders/div.comp
+5 −1 ggml/src/ggml-vulkan/vulkan-shaders/generic_binary_head.comp
+4 −1 ggml/src/ggml-vulkan/vulkan-shaders/generic_unary_head.comp
+3 −3 ggml/src/ggml-vulkan/vulkan-shaders/get_rows.comp
+47 −22 ggml/src/ggml-vulkan/vulkan-shaders/im2col.comp
+1 −1 ggml/src/ggml-vulkan/vulkan-shaders/mul.comp
+53 −71 ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec.comp
+33 −0 ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_base.comp
+76 −74 ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q2_k.comp
+62 −59 ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q3_k.comp
+92 −90 ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q4_k.comp
+122 −120 ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q5_k.comp
+71 −69 ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q6_k.comp
+1 −1 ggml/src/ggml-vulkan/vulkan-shaders/pad.comp
+1 −1 ggml/src/ggml-vulkan/vulkan-shaders/repeat.comp
+1 −1 ggml/src/ggml-vulkan/vulkan-shaders/scale.comp
+2 −2 ggml/src/ggml-vulkan/vulkan-shaders/sin.comp
+2 −2 ggml/src/ggml-vulkan/vulkan-shaders/square.comp
+2 −2 ggml/src/ggml-vulkan/vulkan-shaders/upscale.comp
+2 −1 ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
+26 −0 gguf-py/gguf/constants.py
+1 −0 gguf-py/gguf/tensor_mapping.py
+12 −10 scripts/compare-llama-bench.py
+1 −1 scripts/hf.sh
+1 −1 src/llama-vocab.cpp
+1 −1 src/llama-vocab.h
+298 −2 src/llama.cpp
+13 −1 tests/test-backend-ops.cpp
+4 −0 tests/test-chat-template.cpp

0 comments on commit 7d5c1ba

Please sign in to comment.