ggml-quants, llama : removed excess checks (#7274)

diff --git a/common/common.cpp b/common/common.cpp
index 96130ad54355376817ab83b3e0e6e71efab748a0..e624fc7f35352d39c7c4fcf175d03906869709c0 100644 (file)
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -2553,7 +2553,7 @@ void dump_string_yaml_multiline(FILE * stream, const char * prop_name, const cha
     size_t pos_start = 0;
     size_t pos_found = 0;
 
-    if (!data_str.empty() && (std::isspace(data_str[0]) || std::isspace(data_str.back()))) {
+    if (std::isspace(data_str[0]) || std::isspace(data_str.back())) {
         data_str = std::regex_replace(data_str, std::regex("\n"), "\\n");
         data_str = std::regex_replace(data_str, std::regex("\""), "\\\"");
         data_str = std::regex_replace(data_str, std::regex(R"(\\[^n"])"), R"(\$&)");

diff --git a/ggml-quants.c b/ggml-quants.c
index f13599f6b41bc6df246127ea0fe4d5b88c4da941..9b291d522eba0909bd1a5516f8dcd6378ce8fc4a 100644 (file)
--- a/ggml-quants.c
+++ b/ggml-quants.c
@@ -1986,7 +1986,7 @@ static void quantize_row_q3_K_impl(const float * restrict x, block_q3_K * restri
 
         for (int j = 0; j < QK_K/16; ++j) {
             if (quant_weights) {
-                const float * qw = quant_weights ? quant_weights + QK_K * i + 16*j : NULL;
+                const float * qw = quant_weights + QK_K * i + 16*j;
                 for (int l = 0; l < 16; ++l) weight[l] = qw[l] * sqrtf(sigma2 + x[16*j+l]*x[16*j+l]);
             } else {
                 for (int l = 0; l < 16; ++l) weight[l] = x[16*j+l]*x[16*j+l];

diff --git a/llama.cpp b/llama.cpp
index 0ef756a52860ce8374907934db6f1b04902be31d..daaa138b91caa9932a7b16fc47b05a95ebb505f8 100644 (file)
--- a/llama.cpp
+++ b/llama.cpp
@@ -13904,9 +13904,7 @@ llama_token llama_sample_token_mirostat(struct llama_context * ctx, llama_token_
 
     // Sample the next word X using top-k sampling
     llama_sample_top_k(nullptr, candidates, int(k), 1);
-    if (ctx) {
-        ctx->t_sample_us += ggml_time_us() - t_start_sample_us;
-    }
+    ctx->t_sample_us += ggml_time_us() - t_start_sample_us;
     llama_token X = llama_sample_token(ctx, candidates);
     t_start_sample_us = ggml_time_us();
 
@@ -13920,9 +13918,7 @@ llama_token llama_sample_token_mirostat(struct llama_context * ctx, llama_token_
     // Update mu using the learning rate and error
     *mu = *mu - eta * e;
 
-    if (ctx) {
-        ctx->t_sample_us += ggml_time_us() - t_start_sample_us;
-    }
+    ctx->t_sample_us += ggml_time_us() - t_start_sample_us;
     return X;
 }