Skip to content

Commit

Permalink
llama.cpp updated
Browse files Browse the repository at this point in the history
  • Loading branch information
@mgonzs13
mgonzs13 committed Jul 5, 2024
1 parent 078f208 commit cda1f34
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion llama_ros/llama_cpp
Submodule llama_cpp updated 69 files
+1 −0 .gitignore
+20 −10 CONTRIBUTING.md
+72 −613 README.md
+3 −3 ci/run.sh
+19 −3 common/common.cpp
+1 −0 common/common.h
+5 −22 convert_hf_to_gguf.py
+13 −13 convert_hf_to_gguf_update.py
+56 −0 docs/android.md
+0 −0 docs/backend/BLIS.md
+0 −0 docs/backend/SYCL.md
+288 −0 docs/build.md
+2 −2 docs/development/HOWTO-add-model.md
+0 −0 docs/development/debugging-tests.md
+ − docs/development/llama-star/idea-arch.key
+ − docs/development/llama-star/idea-arch.pdf
+0 −0 docs/development/token_generation_performance_tips.md
+86 −0 docs/docker.md
+39 −0 docs/install.md
+0 −0 examples/convert_legacy_llama.py
+0 −0 examples/finetune/convert_finetune_checkpoint_to_gguf.py
+1 −1 examples/json_schema_pydantic_example.py
+7 −7 examples/llava/MobileVLM-README.md
+10 −10 examples/llava/README.md
+0 −0 examples/llava/convert_image_encoder_to_gguf.py
+0 −0 examples/llava/llava_surgery.py
+0 −0 examples/llava/llava_surgery_v2.py
+1 −1 examples/llava/requirements.txt
+20 −4 examples/main/main.cpp
+3 −0 examples/passkey/README.md
+0 −0 examples/pydantic_models_to_grammar_examples.py
+86 −3 examples/quantize/README.md
+0 −0 examples/regex_to_grammar.py
+1 −1 examples/server/README.md
+0 −0 examples/server_embd.py
+0 −0 examples/train-text-from-scratch/convert_train_checkpoint_to_gguf.py
+2 −1 ggml/src/CMakeLists.txt
+9 −9 ggml/src/ggml-cuda/fattn-common.cuh
+8 −0 ggml/src/ggml-cuda/mmq.cu
+195 −47 ggml/src/ggml-cuda/mmq.cuh
+2 −1 ggml/src/ggml-cuda/template-instances/generate_cu_files.py
+5 −0 ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu
+5 −0 ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu
+14 −29 ggml/src/ggml-cuda/vecdotq.cuh
+5 −270 ggml/src/ggml-sycl.cpp
+1 −0 ggml/src/ggml-sycl/backend.hpp
+2 −13 ggml/src/ggml-sycl/common.hpp
+16 −15 ggml/src/ggml-sycl/dmmv.cpp
+2 −2 ggml/src/ggml-sycl/dpct/helper.hpp
+15 −11 ggml/src/ggml-sycl/norm.cpp
+1 −0 ggml/src/ggml-sycl/presets.hpp
+250 −0 ggml/src/ggml-sycl/softmax.cpp
+24 −0 ggml/src/ggml-sycl/softmax.hpp
+5 −5 gguf-py/README.md
+4 −13 gguf-py/scripts/__init__.py
+0 −0 gguf-py/scripts/gguf_convert_endian.py
+0 −0 gguf-py/scripts/gguf_dump.py
+0 −0 gguf-py/scripts/gguf_new_metadata.py
+0 −0 gguf-py/scripts/gguf_set_metadata.py
+7 −0 include/llama.h
+1 −1 requirements.txt
+1 −1 requirements/requirements-convert_hf_to_gguf.txt
+1 −1 requirements/requirements-convert_hf_to_gguf_update.txt
+0 −0 requirements/requirements-convert_legacy_llama.txt
+1 −1 requirements/requirements-convert_llama_ggml_to_gguf.txt
+5 −5 scripts/check-requirements.sh
+0 −26 scripts/convert-gg.sh
+7 −7 scripts/pod-llama.sh
+198 −174 src/llama.cpp

0 comments on commit cda1f34

Please sign in to comment.