From 4d09e04501baf1562d20fbaa383c3063314c8d45 Mon Sep 17 00:00:00 2001
From: Marcel Coetzee <34739235+Pipboyguy@users.noreply.github.com>
Date: Wed, 11 Mar 2026 16:35:26 +0200
Subject: [PATCH] common : add env vars for cache_type_k/v, mlock,
 k_cache_hadamard and enable env vars for all tools (#1402)

Two changes:

1. Add four missing environment variable bindings to
   gpt_params_parse_from_env():

   - LLAMA_ARG_CACHE_TYPE_K  (string, e.g. "q8_0")
   - LLAMA_ARG_CACHE_TYPE_V  (string, e.g. "q8_0")
   - LLAMA_ARG_MLOCK         (bool, "1"/"true")
   - LLAMA_ARG_K_CACHE_HADAMARD (bool, "1"/"true")

2. Call gpt_params_parse_from_env() from gpt_params_parse() so that
   ALL tools (llama-cli, llama-bench, etc.) respect env vars, not
   just llama-server. Env vars act as defaults; CLI flags override.

Follows the existing get_env() pattern and uses the same
LLAMA_ARG_ prefix convention as the other env vars.

Co-authored-by: Pipboyguy <>
---
 common/common.cpp | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/common/common.cpp b/common/common.cpp
index f4074a61..0eec74ed 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -495,10 +495,15 @@ void gpt_params_parse_from_env(gpt_params & params) {
     get_env("LLAMA_ARG_CONT_BATCHING",    params.cont_batching);
     get_env("LLAMA_ARG_HOST",             params.hostname);
     get_env("LLAMA_ARG_PORT",             params.port);
+    get_env("LLAMA_ARG_CACHE_TYPE_K",     params.cache_type_k);
+    get_env("LLAMA_ARG_CACHE_TYPE_V",     params.cache_type_v);
+    get_env("LLAMA_ARG_MLOCK",            params.use_mlock);
+    get_env("LLAMA_ARG_K_CACHE_HADAMARD", params.k_cache_hadamard);
 
 }
 
 bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
+    gpt_params_parse_from_env(params);
     const auto params_org = params; // the example can modify the default params
 
     try {