red-candle 1.0.1 → 1.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 52c635f005d25a305f99781763a4a3cc03f85fc5b74f0e576e51973ef8306fac
-  data.tar.gz: 1a0ac260a3803f1920ba2d9f71ec361013ae1eb99cf2caed62c0e9aecc583e96
+  metadata.gz: 7405c9911d6088106dd7a19e96312f12b86e9a80087c3d7745cd3911e263890a
+  data.tar.gz: a88b75152708e72e019aba9acfeabd899f1ae1d1c567562ded6d2c6aa8eae8d0
 SHA512:
-  metadata.gz: d301e6ed0fe8ac144c0735288c687f5dd74e7967dbe5d357e550ca5d467f6a33017b2bd9e7f46081711b6bf13555caa3e044183cd74cfaa89151e15c8cdb04a4
-  data.tar.gz: d296c35002b6d0ed919176375e5cc5d93c70fae0c0ae9a02d5cf86b8a4a49a67898c7fbc96e16350bba6792b18792126c976de156fb854b9b4f3260fa052cd79
+  metadata.gz: ce1cc52dc1223968f3398ab0972283a6309a80d306c14193f23336cd36ed55c8fa5eaaaf05d756f76c88e442abe19b0d82d2742a49199930ef6effcffd6d4482
+  data.tar.gz: 8c30f3c0c096f8186b219a9a5d0fe92928621126f545eaabae26ddedc843515b7da8c45890a1f24a7d519c0c68fcd55b0553ea73f977644258ff30c5e5ccd2f1

data/README.md

@@ -60,6 +60,25 @@ end
 - **NER**: Named Entity Recognition directly from Ruby
 - **LLM**: Chat with Large Language Models (e.g., Llama, Mistral, Gemma)
 
+## Model Storage
+
+Models are automatically downloaded and cached when you first use them. They are stored in:
+- **Location**: `~/.cache/huggingface/hub/`
+- **Size**: Models range from ~100MB (embeddings) to several GB (LLMs)
+- **Reuse**: Models are downloaded once and reused across sessions
+
+To check your cache or manage storage:
+```bash
+# View cache contents
+ls -la ~/.cache/huggingface/hub/
+
+# Check total cache size
+du -sh ~/.cache/huggingface/
+
+# Clear cache if needed (removes all downloaded models)
+rm -rf ~/.cache/huggingface/hub/
+```
+
 ----
 
 ## Usage
@@ -194,7 +213,7 @@ llm = Candle::LLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0", device:
 # Metal
 device = Candle::Device.metal 
 
-# CUDA support (for NVIDIA GPUs COMING SOON)
+# CUDA support (for NVIDIA GPUs)
 device = Candle::Device.cuda   # Linux/Windows with NVIDIA GPU
 ```
 
@@ -840,7 +859,7 @@ Pull requests are welcome.
 2. `bundle exec rake build`
 3. `git tag VERSION_NUMBER`
 4. `git push --follow-tags`
-5. `gem push pkg/red-candle-1.0.0.gem`
+5. `gem push pkg/red-candle-VERSION_NUMBER.gem`
 
 ## See Also
 

data/ext/candle/build.rs

@@ -16,6 +16,7 @@ fn main() {
     println!("cargo:rerun-if-env-changed=CUDA_PATH");
     println!("cargo:rerun-if-env-changed=CANDLE_FEATURES");
     println!("cargo:rerun-if-env-changed=CANDLE_ENABLE_CUDA");
+    println!("cargo:rerun-if-env-changed=CANDLE_DISABLE_CUDA");
 
     // Check if we should force CPU only
     if env::var("CANDLE_FORCE_CPU").is_ok() {
@@ -26,13 +27,13 @@ fn main() {
 
     // Detect CUDA availability
     let cuda_available = detect_cuda();
-    let cuda_enabled = env::var("CANDLE_ENABLE_CUDA").is_ok();
+    let cuda_disabled = env::var("CANDLE_DISABLE_CUDA").is_ok();
     
-    if cuda_available && cuda_enabled {
+    if cuda_available && !cuda_disabled {
         println!("cargo:rustc-cfg=has_cuda");
-        println!("cargo:warning=CUDA detected and enabled via CANDLE_ENABLE_CUDA");
-    } else if cuda_available && !cuda_enabled {
-        println!("cargo:warning=CUDA detected but not enabled. To enable CUDA support (coming soon), set CANDLE_ENABLE_CUDA=1");
+        println!("cargo:warning=CUDA detected, CUDA acceleration will be available");
+    } else if cuda_available && cuda_disabled {
+        println!("cargo:warning=CUDA detected but disabled via CANDLE_DISABLE_CUDA");
     }
 
     // Detect Metal availability (macOS only)

data/ext/candle/extconf.rb

@@ -15,10 +15,10 @@ else
                     (File.exist?('C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA') ||
                      File.exist?('C:\CUDA')))
   
-  cuda_enabled = ENV['CANDLE_ENABLE_CUDA']
+  cuda_disabled = ENV['CANDLE_DISABLE_CUDA']
   
-  if cuda_available && cuda_enabled
-    puts "CUDA detected and enabled via CANDLE_ENABLE_CUDA"
+  if cuda_available && !cuda_disabled
+    puts "CUDA detected, enabling CUDA support"
     features << 'cuda'
     
     # Check if CUDNN should be enabled
@@ -26,10 +26,9 @@ else
       puts "CUDNN support enabled"
       features << 'cudnn'
     end
-  elsif cuda_available && !cuda_enabled
+  elsif cuda_available && cuda_disabled
     puts "=" * 80
-    puts "CUDA detected but not enabled."
-    puts "To enable CUDA support (coming soon), set CANDLE_ENABLE_CUDA=1"
+    puts "CUDA detected but disabled via CANDLE_DISABLE_CUDA"
     puts "=" * 80
   end
 

data/lib/candle/build_info.rb

@@ -15,8 +15,8 @@ module Candle
         if cuda_potentially_available
           warn "=" * 80
           warn "Red Candle: CUDA detected on system but not enabled in build."
-          warn "To enable CUDA support (experimental), reinstall with:"
-          warn "  CANDLE_ENABLE_CUDA=1 gem install red-candle"
+          warn "This may be due to CANDLE_DISABLE_CUDA being set during installation."
+          warn "To enable CUDA support, reinstall without CANDLE_DISABLE_CUDA set."
           warn "=" * 80
         end
         # :nocov:

data/lib/candle/version.rb

@@ -1,5 +1,5 @@
 # :nocov:
 module Candle
-  VERSION = "1.0.1"
+  VERSION = "1.0.2"
 end
 # :nocov:

data/lib/red-candle.rb

@@ -0,0 +1 @@
+require 'candle'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: red-candle
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.0.2
 platform: ruby
 authors:
 - Christopher Petersen
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-07-19 00:00:00.000000000 Z
+date: 2025-07-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys
@@ -197,6 +197,7 @@ files:
 - lib/candle/tensor.rb
 - lib/candle/tokenizer.rb
 - lib/candle/version.rb
+- lib/red-candle.rb
 homepage: https://github.com/assaydepot/red-candle
 licenses:
 - MIT