Commit df66523
- .github/workflows/release.yml+1
- common/arg.cpp+3-3
- common/json-schema-to-grammar.cpp+23-23
- common/peg-parser.cpp+121-81
- common/peg-parser.h+2-2
- common/speculative.cpp+102-35
- examples/json_schema_to_grammar.py+21-21
- ggml/src/ggml-hexagon/htp/ssm-conv.c+10-9
- include/llama.h+9-8
- src/llama-context.cpp+8
- src/llama-context.h+1
- src/llama-cparams.h+2
- src/llama-ext.h+5
- src/llama-graph.h+9-2
- src/llama-model.cpp+4
- src/llama-quant.cpp+2-2
- src/models/step35.cpp+28-29
- tests/peg-parser/test-gbnf-generation.cpp+79-1
- tests/test-arg-parser.cpp+11-1
- tests/test-chat.cpp+2-2
- tests/test-json-schema-to-grammar.cpp+155-155
- tools/server/README.md+26-2
- tools/server/server-context.cpp+56-1
- tools/server/server-models.cpp+17-3
- tools/server/server-models.h+7-1
- tools/server/server-schema.cpp+3
- tools/server/server-tools.cpp+1
- tools/server/tests/unit/test_chat_completion.py+20
0 commit comments