chore: bump airframe dep to 0.2.12, shimmy v2.3.3

Author: Michael-A-Kuykendall

Cargo.lock

@@ -1,109 +1,109 @@
-[package]
-name = "shimmy"
-version = "2.3.2"
-edition = "2021"
-license = "MIT"
-description = "Lightweight Ollama-compatible inference server with native SafeTensors support. No Python dependencies, cross-platform WebGPU acceleration via Airframe."
-homepage = "https://github.com/Michael-A-Kuykendall/shimmy"
-repository = "https://github.com/Michael-A-Kuykendall/shimmy"
-readme = "README.md"
-keywords = ["llm", "local-ai", "inference", "server", "api"]
-categories = ["command-line-utilities", "web-programming::http-server"]
-authors = ["Michael A. Kuykendall <michaelallenkuykendall@gmail.com>"]
-include = [
-    "src/**/*",
-    "templates/**/*",
-    "Cargo.toml",
-    "Cargo.lock",
-    "README.md",
-    "LICENSE",
-    "build.rs"
-]
-
-[features]
-default = ["airframe", "huggingface"]  # Full GPU build; use --no-default-features --features huggingface for CPU-only
-# Engine backends
-airframe = ["dep:airframe"]  # Airframe native GPU engine
-huggingface = [] # Python integration, no additional Rust deps
-mlx = [] # Apple MLX integration for Metal GPU acceleration on Apple Silicon
-# Convenience feature sets
-fast = ["huggingface"] # Fast compilation - no path deps (CI-safe)
-full = ["airframe", "huggingface", "mlx"] # Full compilation - includes all backends
-gpu = ["airframe", "huggingface"] # GPU-optimized build via Airframe
-apple = ["airframe", "huggingface"] # Apple Silicon - Airframe via Metal + HuggingFace
-coverage = ["huggingface"] # Coverage testing - no path deps, fast compile
-llama = [] # Deprecated: llama.cpp removed in v2.0. Empty feature retained to silence cfg guards pending cleanup.
-llama-cuda = [] # Deprecated: llama.cpp CUDA backend removed in v2.0.
-llama-vulkan = [] # Deprecated: llama.cpp Vulkan backend removed in v2.0.
-llama-opencl = [] # Deprecated: llama.cpp OpenCL backend removed in v2.0.
-
-[dependencies]
-anyhow = "1"
-axum = { version = "0.7", features = ["http1", "json", "ws", "macros"] }
-async-trait = "0.1"
-bytes = "1"
-chrono = { version = "0.4", features = ["serde"] }
-clap = { version = "4", features = ["derive"] }
-futures-util = "0.3"
-lazy_static = "1.5"
-memmap2 = "0.9"
-minijinja = { version = "2", features = ["loader"] }
-parking_lot = "0.12"
-rand = "0.8"
-regex = "1"
-safetensors = "0.4"
-serde = { version = "1", features = ["derive"] }
-serde_json = "1"
-sys-info = "0.9"
-sysinfo = "0.30"
-tempfile = "3"
-thiserror = "1"
-tokio = { version = "1", features = ["macros","rt-multi-thread","signal","process","fs"] }
-tokio-stream = "0.1"
-tracing = "0.1"
-tracing-subscriber = { version = "0.3.20", features = ["env-filter"] }
-uuid = { version = "1", features = ["v4", "serde"] }
-dirs = "5.0"
-reqwest = { version = "0.12", features = ["json", "rustls-tls", "stream"], default-features = false }
-
-# Airframe native GPU inference — public crate on crates.io
-airframe = { version = "0.2.11", optional = true, features = ["isf"] }
-
-[dev-dependencies]
-tokio-tungstenite = "0.20"
-criterion = { version = "0.5", features = ["html_reports"] }
-serial_test = "3.1"  # For serialized test execution
-# Additional dependencies for mock testing infrastructure
-tempfile = "3"  # For creating temporary test directories
-rand = "0.8"    # For randomized testing scenarios (already in main deps)
-assert_cmd = "2"  # For CLI testing
-predicates = "3"  # For assertion predicates in tests
-tower = { version = "0.5", features = ["util"] }  # For test oneshot helper
-# Note: tempfile is already in main dependencies, rand is already in main dependencies
-
-[profile.release]
-lto = true
-codegen-units = 1
-opt-level = "z"
-
-# Optimize build times for development
-[profile.dev]
-opt-level = 1
-debug = true
-
-# Faster builds for dependencies
-[profile.dev.package."*"]
-opt-level = 2
-debug = false
-
-# Benchmark configuration  
-[[bench]]
-name = "model_loading"
-harness = false
-
-[[bench]]
-name = "generation_performance"
-harness = false
-
-[workspace]
-
+[package]
+name = "shimmy"
+version = "2.3.3"
+edition = "2021"
+license = "MIT"
+description = "Lightweight Ollama-compatible inference server with native SafeTensors support. No Python dependencies, cross-platform WebGPU acceleration via Airframe."
+homepage = "https://github.com/Michael-A-Kuykendall/shimmy"
+repository = "https://github.com/Michael-A-Kuykendall/shimmy"
+readme = "README.md"
+keywords = ["llm", "local-ai", "inference", "server", "api"]
+categories = ["command-line-utilities", "web-programming::http-server"]
+authors = ["Michael A. Kuykendall <michaelallenkuykendall@gmail.com>"]
+include = [
+    "src/**/*",
+    "templates/**/*",
+    "Cargo.toml",
+    "Cargo.lock",
+    "README.md",
+    "LICENSE",
+    "build.rs"
+]
+
+[features]
+default = ["airframe", "huggingface"]  # Full GPU build; use --no-default-features --features huggingface for CPU-only
+# Engine backends
+airframe = ["dep:airframe"]  # Airframe native GPU engine
+huggingface = [] # Python integration, no additional Rust deps
+mlx = [] # Apple MLX integration for Metal GPU acceleration on Apple Silicon
+# Convenience feature sets
+fast = ["huggingface"] # Fast compilation - no path deps (CI-safe)
+full = ["airframe", "huggingface", "mlx"] # Full compilation - includes all backends
+gpu = ["airframe", "huggingface"] # GPU-optimized build via Airframe
+apple = ["airframe", "huggingface"] # Apple Silicon - Airframe via Metal + HuggingFace
+coverage = ["huggingface"] # Coverage testing - no path deps, fast compile
+llama = [] # Deprecated: llama.cpp removed in v2.0. Empty feature retained to silence cfg guards pending cleanup.
+llama-cuda = [] # Deprecated: llama.cpp CUDA backend removed in v2.0.
+llama-vulkan = [] # Deprecated: llama.cpp Vulkan backend removed in v2.0.
+llama-opencl = [] # Deprecated: llama.cpp OpenCL backend removed in v2.0.
+
+[dependencies]
+anyhow = "1"
+axum = { version = "0.7", features = ["http1", "json", "ws", "macros"] }
+async-trait = "0.1"
+bytes = "1"
+chrono = { version = "0.4", features = ["serde"] }
+clap = { version = "4", features = ["derive"] }
+futures-util = "0.3"
+lazy_static = "1.5"
+memmap2 = "0.9"
+minijinja = { version = "2", features = ["loader"] }
+parking_lot = "0.12"
+rand = "0.8"
+regex = "1"
+safetensors = "0.4"
+serde = { version = "1", features = ["derive"] }
+serde_json = "1"
+sys-info = "0.9"
+sysinfo = "0.30"
+tempfile = "3"
+thiserror = "1"
+tokio = { version = "1", features = ["macros","rt-multi-thread","signal","process","fs"] }
+tokio-stream = "0.1"
+tracing = "0.1"
+tracing-subscriber = { version = "0.3.20", features = ["env-filter"] }
+uuid = { version = "1", features = ["v4", "serde"] }
+dirs = "5.0"
+reqwest = { version = "0.12", features = ["json", "rustls-tls", "stream"], default-features = false }
+
+# Airframe native GPU inference — public crate on crates.io
+airframe = { version = "0.2.12", optional = true, features = ["isf"] }
+
+[dev-dependencies]
+tokio-tungstenite = "0.20"
+criterion = { version = "0.5", features = ["html_reports"] }
+serial_test = "3.1"  # For serialized test execution
+# Additional dependencies for mock testing infrastructure
+tempfile = "3"  # For creating temporary test directories
+rand = "0.8"    # For randomized testing scenarios (already in main deps)
+assert_cmd = "2"  # For CLI testing
+predicates = "3"  # For assertion predicates in tests
+tower = { version = "0.5", features = ["util"] }  # For test oneshot helper
+# Note: tempfile is already in main dependencies, rand is already in main dependencies
+
+[profile.release]
+lto = true
+codegen-units = 1
+opt-level = "z"
+
+# Optimize build times for development
+[profile.dev]
+opt-level = 1
+debug = true
+
+# Faster builds for dependencies
+[profile.dev.package."*"]
+opt-level = 2
+debug = false
+
+# Benchmark configuration  
+[[bench]]
+name = "model_loading"
+harness = false
+
+[[bench]]
+name = "generation_performance"
+harness = false
+
+[workspace]
+