Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/python-type-check.yml
#	AGENTS.md
#	CONTRIBUTING.md
#	examples/model-conversion/scripts/embedding/run-original-model.py
#	examples/model-conversion/scripts/utils/compare_tokens.py
#	examples/pydantic_models_to_grammar.py
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	pyrightconfig.json
#	scripts/compare-llama-bench.py
#	scripts/jinja/jinja-tester.py
#	scripts/server-bench.py
#	tests/test-grammar-integration.cpp
#	tests/test-grammar-parser.cpp
#	tests/test-llama-grammar.cpp
#	tests/test-tokenizer-random.py
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2026-03-22 23:39:13 +08:00
18 changed files with 204 additions and 108 deletions
+1 -1
View File
@@ -2586,7 +2586,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
{"-hf", "-hfr", "--hf-repo"}, "<user>/<model>[:quant]",
"Hugging Face model repository; quant is optional, case-insensitive, default to Q4_K_M, or falls back to the first file in the repo if Q4_K_M doesn't exist.\n"
"mmproj is also downloaded automatically if available. to disable, add --no-mmproj\n"
"example: unsloth/phi-4-GGUF:q4_k_m\n"
"example: ggml-org/GLM-4.7-Flash-GGUF:Q4_K_M\n"
"(default: unused)",
[](common_params & params, const std::string & value) {
params.model.hf_repo = value;