diff --git a/crates/ml-core/Cargo.toml b/crates/ml-core/Cargo.toml
index d3101e164..f73a9be4f 100644
--- a/crates/ml-core/Cargo.toml
+++ b/crates/ml-core/Cargo.toml
@@ -14,7 +14,7 @@ categories.workspace = true
 description = "Shared ML types, traits, and infrastructure for Foxhunt"
 
 [features]
-default = ["cuda"]
+default = []
 cuda = ["candle-core/cuda", "candle-nn/cuda"]
 s3-storage = ["aws-config", "aws-sdk-s3", "aws-types", "aws-credential-types", "urlencoding"]
 high-precision = ["rust_decimal/serde-float"]
diff --git a/crates/ml-dqn/Cargo.toml b/crates/ml-dqn/Cargo.toml
index 3f7ad260b..ea1c4f15a 100644
--- a/crates/ml-dqn/Cargo.toml
+++ b/crates/ml-dqn/Cargo.toml
@@ -14,7 +14,7 @@ categories.workspace = true
 description = "DQN reinforcement learning for Foxhunt trading"
 
 [features]
-default = ["cuda"]
+default = []
 cuda = ["candle-core/cuda", "candle-nn/cuda"]
 
 [dependencies]
diff --git a/crates/ml-ensemble/Cargo.toml b/crates/ml-ensemble/Cargo.toml
index 031da7a09..1cbd689a1 100644
--- a/crates/ml-ensemble/Cargo.toml
+++ b/crates/ml-ensemble/Cargo.toml
@@ -14,7 +14,7 @@ categories.workspace = true
 description = "ML ensemble coordination — voting, confidence, gating, hot-swap, inference pipeline"
 
 [features]
-default = ["cuda"]
+default = []
 cuda = ["candle-core/cuda"]
 
 [dependencies]
diff --git a/crates/ml-explainability/Cargo.toml b/crates/ml-explainability/Cargo.toml
index bdd63ad39..efe076733 100644
--- a/crates/ml-explainability/Cargo.toml
+++ b/crates/ml-explainability/Cargo.toml
@@ -14,7 +14,7 @@ categories.workspace = true
 description = "Model explainability (integrated gradients) for Foxhunt ML"
 
 [features]
-default = ["cuda"]
+default = []
 cuda = ["candle-core/cuda", "candle-nn/cuda"]
 
 [dependencies]
diff --git a/crates/ml-hyperopt/Cargo.toml b/crates/ml-hyperopt/Cargo.toml
index 7c9bbdcb3..a022fd360 100644
--- a/crates/ml-hyperopt/Cargo.toml
+++ b/crates/ml-hyperopt/Cargo.toml
@@ -14,7 +14,7 @@ categories.workspace = true
 description = "ML hyperparameter optimization — PSO, TPE, campaigns, sensitivity analysis"
 
 [features]
-default = ["cuda"]
+default = []
 cuda = ["candle-core/cuda"]
 
 [dependencies]
diff --git a/crates/ml-labeling/Cargo.toml b/crates/ml-labeling/Cargo.toml
index 51712f762..4b27965f1 100644
--- a/crates/ml-labeling/Cargo.toml
+++ b/crates/ml-labeling/Cargo.toml
@@ -14,7 +14,7 @@ categories.workspace = true
 description = "ML labeling algorithms for Foxhunt HFT training data"
 
 [features]
-default = ["cuda"]
+default = []
 cuda = ["candle-core/cuda"]
 
 [dependencies]
diff --git a/crates/ml-ppo/Cargo.toml b/crates/ml-ppo/Cargo.toml
index 48bf2c2cd..252687654 100644
--- a/crates/ml-ppo/Cargo.toml
+++ b/crates/ml-ppo/Cargo.toml
@@ -14,7 +14,7 @@ categories.workspace = true
 description = "PPO reinforcement learning for Foxhunt trading"
 
 [features]
-default = ["cuda"]
+default = []
 cuda = ["candle-core/cuda", "candle-nn/cuda"]
 
 [dependencies]
diff --git a/crates/ml-supervised/Cargo.toml b/crates/ml-supervised/Cargo.toml
index 91ca87807..35f10beb5 100644
--- a/crates/ml-supervised/Cargo.toml
+++ b/crates/ml-supervised/Cargo.toml
@@ -14,7 +14,7 @@ categories.workspace = true
 description = "Supervised models (TFT, Mamba, Liquid, TGGN, TLOB, KAN, xLSTM, Diffusion)"
 
 [features]
-default = ["cuda"]
+default = []
 cuda = ["candle-core/cuda", "candle-nn/cuda"]
 
 [dependencies]