Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 16:55:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/nix/package-gguf-py.nix
#	.devops/nix/scope.nix
#	common/CMakeLists.txt
#	docs/backend/SYCL.md
#	examples/lookahead/lookahead.cpp
#	examples/lookup/lookup.cpp
#	examples/sycl/run-llama2.sh
#	examples/sycl/win-run-llama2.bat
#	examples/sycl/win-test.bat
#	ggml/src/ggml-hexagon/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hvx-dump.h
#	ggml/src/ggml-hexagon/htp/hvx-reduce.h
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/softmax-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	scripts/sync-ggml.last
This commit is contained in:
Concedo
2026-02-01 22:35:25 +08:00
parent 76b22a7b23 2634ed207a
commit ddce19db72
19 changed files with 377 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+3 -1
View File
@@ -3399,7 +3399,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"--spec-type"}, "[none|ngram-cache|ngram-simple|ngram-map-k|ngram-map-k4v]",
{"--spec-type"}, "[none|ngram-cache|ngram-simple|ngram-map-k|ngram-map-k4v|ngram-mod]",
string_format("type of speculative decoding to use when no draft model is provided (default: %s)\n",
common_speculative_type_to_str(params.speculative.type).c_str()),
[](common_params & params, const std::string & value) {
@@ -3413,6 +3413,8 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.speculative.type = COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K;
} else if (value == "ngram-map-k4v") {
params.speculative.type = COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V;
} else if (value == "ngram-mod") {
params.speculative.type = COMMON_SPECULATIVE_TYPE_NGRAM_MOD;
} else {
throw std::invalid_argument("unknown speculative decoding type without draft model");
}