File tree
3 files changed
+9
-4
lines changed- Sources
- LocalLLMClientLlamaC/exclude
 - LocalLLMClientLlama
 
 
3 files changed
+9
-4
lines changed| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
 | |||
2 | 2 |  | |
3 | 3 |  | |
4 | 4 |  | |
5 |  | - | |
 | 5 | + | |
6 | 6 |  | |
7 | 7 |  | |
8 | 8 |  | |
 | |||
94 | 94 |  | |
95 | 95 |  | |
96 | 96 |  | |
97 |  | - | |
 | 97 | + | |
98 | 98 |  | |
99 | 99 |  | |
100 | 100 |  | |
 | |||
159 | 159 |  | |
160 | 160 |  | |
161 | 161 |  | |
162 |  | - | |
 | 162 | + | |
163 | 163 |  | |
164 | 164 |  | |
165 | 165 |  | |
 | |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
 | |||
5 | 5 |  | |
6 | 6 |  | |
7 | 7 |  | |
 | 8 | + | |
8 | 9 |  | |
9 | 10 |  | |
10 | 11 |  | |
 | |||
20 | 21 |  | |
21 | 22 |  | |
22 | 23 |  | |
 | 24 | + | |
 | 25 | + | |
 | 26 | + | |
 | 27 | + | |
23 | 28 |  | |
24 | 29 |  | |
25 | 30 |  | |
 | |||
- .github/workflows/build.yml+4-4
 - .github/workflows/release.yml+12-5
 - .github/workflows/server.yml+1-1
 - CMakeLists.txt+5
 - README.md+31-11
 - ci/run.sh+14-1
 - common/arg.cpp+1
 - common/chat.cpp+8-7
 - common/chat.h+1-1
 - common/common.cpp+2-2
 - common/common.h+2-1
 - common/speculative.cpp+6-4
 - convert_hf_to_gguf.py+1-2
 - docs/build.md+4
 - docs/install.md+20-16
 - examples/batched.swift/Sources/main.swift+1-1
 - examples/embedding/embedding.cpp+18-3
 - examples/gritlm/gritlm.cpp+2-2
 - examples/llama.android/llama/src/main/cpp/llama-android.cpp+4-4
 - examples/llama.swiftui/llama.cpp.swift/LibLlama.swift+4-4
 - examples/lookahead/lookahead.cpp+8-6
 - examples/lookup/lookup.cpp+1-1
 - examples/parallel/parallel.cpp+7-5
 - examples/passkey/passkey.cpp+11-9
 - examples/retrieval/retrieval.cpp+1-1
 - examples/save-load-state/save-load-state.cpp+1-1
 - examples/simple-chat/simple-chat.cpp+2-2
 - examples/speculative-simple/speculative-simple.cpp+1-1
 - examples/speculative/speculative.cpp+14-12
 - ggml/CMakeLists.txt+1-1
 - ggml/src/CMakeLists.txt-1
 - ggml/src/ggml-cpu/ops.cpp+2-2
 - ggml/src/ggml-cuda/fattn-mma-f16.cuh+4-1
 - ggml/src/ggml-metal/ggml-metal.m+5-3
 - ggml/src/ggml-metal/ggml-metal.metal+52-42
 - ggml/src/ggml-opencl/CMakeLists.txt+6
 - ggml/src/ggml-opencl/ggml-opencl.cpp+747-3
 - ggml/src/ggml-opencl/kernels/concat.cl+109
 - ggml/src/ggml-opencl/kernels/pad.cl+30
 - ggml/src/ggml-opencl/kernels/repeat.cl+39
 - ggml/src/ggml-opencl/kernels/tanh.cl+63
 - ggml/src/ggml-opencl/kernels/tsembd.cl+48
 - ggml/src/ggml-opencl/kernels/upscale.cl+121
 - ggml/src/ggml-vulkan/ggml-vulkan.cpp+162-34
 - ggml/src/ggml-vulkan/vulkan-shaders/conv_transpose_1d.comp+98
 - ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp+2
 - gguf-py/gguf/gguf_writer.py+3
 - include/llama.h+124-29
 - src/CMakeLists.txt-1
 - src/llama-context.cpp+240-109
 - src/llama-context.h+8-6
 - src/llama-graph.cpp+2-3
 - src/llama-graph.h+1-1
 - src/llama-kv-cache-recurrent.cpp+16-16
 - src/llama-kv-cache-recurrent.h+13-19
 - src/llama-kv-cache-unified-iswa.cpp+34-31
 - src/llama-kv-cache-unified-iswa.h+22-24
 - src/llama-kv-cache-unified.cpp+141-86
 - src/llama-kv-cache-unified.h+66-37
 - src/llama-kv-cache.cpp-1
 - src/llama-kv-cache.h-44
 - src/llama-memory.cpp+41
 - src/llama-memory.h+65-23
 - src/llama-mmap.cpp+1-1
 - src/llama-model-loader.cpp+42-17
 - src/llama-model.cpp+38-10
 - src/llama-model.h+3
 - src/llama-vocab.cpp+5-1
 - tests/test-backend-ops.cpp+14-2
 - tests/test-chat.cpp+1-1
 - tools/batched-bench/batched-bench.cpp+4-2
 - tools/cvector-generator/cvector-generator.cpp+1-1
 - tools/imatrix/imatrix.cpp+1-1
 - tools/llama-bench/llama-bench.cpp+2-2
 - tools/main/main.cpp+8-6
 - tools/mtmd/mtmd-cli.cpp+1-1
 - tools/perplexity/perplexity.cpp+6-6
 - tools/run/run.cpp+2-2
 - tools/server/server.cpp+17-15
 - tools/server/tests/unit/test_tool_call.py+6-7
 - tools/server/tests/utils.py+10-1
 
0 commit comments