[package]
name = "makepad-ai-llm"
version = "0.1.0"
edition = "2021"
description = "GGUF LLM family (Qwen). Graph builders + Metal/CUDA exec. Was libs/llama (aiarch.md §1)."
license = "MIT"

[dependencies]
# Bake the metallib at build time. Without this, MetalRuntime::new() compiles
# the 13k-line shader source on the GPU and can stall WindowServer.
makepad-ai-loader = { path = "../loader" }
makepad-ai-cuda = { path = "../cuda" }
makepad-ai-metal = { path = "../metal", features = ["metal-precompile"] }

[[bin]]
name = "llama-load"
path = "src/bin/llama_load.rs"

[[bin]]
name = "llama-load-time"
path = "src/bin/llama_load_time.rs"

[[bin]]
name = "llama-graph-census"
path = "src/bin/llama_graph_census.rs"

[[bin]]
name = "llama-cuda-canary"
path = "src/bin/llama_cuda_canary.rs"

[[bin]]
name = "llama-compare"
path = "src/bin/llama_compare.rs"

[[bin]]
name = "llama-generate"
path = "src/bin/llama_generate.rs"

[[bin]]
name = "llama-tokenize"
path = "src/bin/llama_tokenize.rs"

[[bin]]
name = "llama-slot-probe"
path = "src/bin/llama_slot_probe.rs"

[[bin]]
name = "llama-lane-spec-probe"
path = "src/bin/llama_lane_spec_probe.rs"

[[bin]]
name = "llama-batch-probe"
path = "src/bin/llama_batch_probe.rs"

# The decode column-cost curve: what an extra batch column actually costs,
# which is what sets how many chats one card can serve.
[[bin]]
name = "llama-batch-bench"
path = "src/bin/llama_batch_bench.rs"

[[bin]]
name = "vlm-vision-probe"
path = "src/bin/vlm_vision_probe.rs"

[[bin]]
name = "vlm-probe"
path = "src/bin/vlm_probe.rs"

# Batch executor for the asset-annotation pass (libs/asset/annotate): one
# resident model, many sheets, line-oriented job/result files.
[[bin]]
name = "vlm-annotate"
path = "src/bin/vlm_annotate.rs"

[[bin]]
name = "llama-reset-probe"
path = "src/bin/llama_reset_probe.rs"