mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-09-18 16:55:14 +02:00
Merge commit 'c1258830b28dddc65ac3aa3452214553fdece30c' into concedo_experimental
# Conflicts: # docs/docker.md # docs/ops.md # docs/ops/WebGPU.csv # ggml/src/ggml-cann/aclnn_ops.cpp # ggml/src/ggml-cann/ggml-cann.cpp # ggml/src/ggml-cpu/CMakeLists.txt # ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp # ggml/src/ggml-webgpu/ggml-webgpu.cpp # ggml/src/ggml-webgpu/wgsl-shaders/get_rows.wgsl # ggml/src/ggml-webgpu/wgsl-shaders/row_norm.wgsl # ggml/src/ggml-webgpu/wgsl-shaders/unary.wgsl
This commit is contained in:
+1
-1
@@ -3497,7 +3497,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
||||
throw std::invalid_argument("unknown speculative decoding type without draft model");
|
||||
}
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}));
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_SPEC_TYPE"));
|
||||
add_opt(common_arg(
|
||||
{"--spec-ngram-size-n"}, "N",
|
||||
string_format("ngram size N for ngram-simple/ngram-map speculative decoding, length of lookup n-gram (default: %d)", params.speculative.ngram_size_n),
|
||||
|
||||
Reference in New Issue
Block a user