mirror of
				https://github.com/ggml-org/llama.cpp.git
				synced 2025-10-30 08:42:00 +00:00 
			
		
		
		
	llama : minor sampling refactor (2) (#9386)
This commit is contained in:
		| @@ -118,8 +118,6 @@ int main(int argc, char ** argv) { | ||||
|         { | ||||
|             const llama_token new_token_id = llama_sampler_sample(smpl, ctx, batch.n_tokens - 1); | ||||
|  | ||||
|             llama_sampler_accept(smpl, new_token_id); | ||||
|  | ||||
|             // is it an end of generation? | ||||
|             if (llama_token_is_eog(model, new_token_id) || n_cur == n_predict) { | ||||
|                 LOG_TEE("\n"); | ||||
|   | ||||
		Reference in New Issue
	
	Block a user
	 slaren
					slaren