e37c263b9c
Squashed from work: - asset-ai: FastH3 4-step fast video backend; clip keyframes on the wire - asset-ui: loop video chains — text→image→video that ends where it began - h3: safetensors -> pruned-Q4_K GGUF quantizer for the 24GB DiT tiers - h3_quant_gguf verify: row-error gates calibrated to the measured Q4_K floor - asset-ai realtime: the feedback loop — the source anchors, the drifted frame inits - asset-ai realtime: a feedback loop survives a resize and travels by default - asset-ai realtime: the feedback loop frees itself from the feed handshake and pauses for its listener - asset-ai realtime: the outbound encode leaves the loop's critical path - asset-ai ocr: the ocr domain — Chandra 2 at page resolution, and the tower goes planner-owned - llm slots: a lane can hold an image span — embedding prefill and a rope cursor of its own - vision tower on CUDA: the encode leg gets its two missing kernels - llm/ocr: one M-RoPE grid encoder for both image paths, and a livelock made an error - vision tower on CUDA: the f16 GEMM keeps the precision it was throwing away - live: a feed that moves box takes its trip with it — one seed image - vision tower on CUDA: the tiled attention becomes bit-exact, and tensor cores go - llm prefill on CUDA: the MMA attention kernel gets the tile a 4-to-1 model needs - asset-ai ocr: the CUDA encode lane joins the integration — vision-parity sits beside run's three arms, and the kernels - Merge branch 'ocr-perf-integration' into work - asset-ai: the live anchor can follow the trip, and text leaves the 5090 - asset-ai: the camera moves the world, and the world starts still - asset-import: the EA strategy classics, in the one 2D contract - rtsmap: one seeded generator for tiled strategy maps - asset-ui: one card for the strategy classics, with a pack dropdown - asset-ai: music3 reference-audio path, ocr/h3 backends, registry - asset: mp4 sample index for range-streaming, chat tools, import profiles - cnc: tiberium is twelve growth frames, not twelve empty variants - platform: native file and save dialogs, in-house on all three desktops - chat: the scan holds out for a lane home - chat: a full home queues you — take the free lane - chat: the preload has a percentage, and the boundless cap stops showing - llm cuda: the 32x2 attention tile — even GQA ratios stay on MMA - sa3 gets a bake path: the sfx model's tables precomputed by a diffusion-side bin - sqlite_query: anti-join regression test - td import: HARV's second frame block is its harvesting cycle, not a turret - asset-ui: sprite enhancement runs on the 32B dev DiT — distillation, not the prompt, was the ceiling - ai-hub: makepad-asset-ai becomes makepad-ai-hub at libs/ai/hub, the chat pane becomes makepad-chat-ui, the service bin - asset-ui: test health fixtures grow the realtime field they were born without - ai-hub: one home at ~/.makepad — weights/ run/ cache/ logs/, the service cache migrates from ai_content by a single re - ai-hub: subprocess workers die with the node — process groups everywhere, PDEATHSIG on linux, one KILL_ON_JOB_CLOSE Jo - ai-hub: the hub object — AiHub::in_process, pipes vocabulary, and the local LLM engine generalized out of mpfiles (aic - strict-json: the dependency-free JSON module gets its own crate; asset-client re-exports it so nothing downstream move - ai-hub: the machine layer — node entries, the 0600 machine token, and the residency election that IS the lock (aicore - ai-hub: MPHUB1 — the fabric beacon only dedicated nodes can send (aicore §4) - ai-hub: job leases — work lives only while it is renewed (aicore §8) - asset-creator: the pipeline library is born — specs, the deps gate, and the derived-state law (aicore §9) - ai-hub: RAM residency facts — the CPU-side twin of residency.rs (aicore §3) - ai-hub: ETA placement primitives — relative GPU throughput, the four-term estimate, and an observable breakdown (aicor - ai-hub: leases go live on the wire — origin fields on submit, /job/<id>/keepalive, /bye, and the reaper that cancels w - ai-hub: the chat providers move in — fleet qwen, openai, grok, claude/codex/grok CLIs, the responses driver, and the w - asset-creator: the engine — one pipeline run against the hub, deps-gated, spliced, cancellable, resumable-by-construct - ai-hub: the machine node mode — --machine binds loopback, registers in ~/.makepad/run, and exits on its own once idle - asset-creator: makepad-creator-run — the detached client for runs that must outlive a window (aicore §9) - ai-hub: a native Claude Messages-API provider — API-key or Claude Code OAuth, bounded SSE streaming, injected tools (a - route + converse: off makepad_ai — the Agent seam moves to converse, route's cloud dispatcher rides the hub's Claude p - asset-creator: the preset tables move in — fifteen chain-policy constants shared by every creator app (aicore §9 / P6) - makepad_ai is deleted — every backend is a hub pipe, the agent seam lives with its consumers (aicore §14, decided 2026 - ai-hub: loads hold the machine residency election — set_model_state claims on Loaded and publishes the service port (a - ai-hub: chats run the machine election — route to a serving holder, wait on a loading one, claim and publish when open - ai-hub: pick_for_domain_eta — ETA-ranked placement over the shared hard-filter core (aicore §6 / P4) - asset-creator: the engine picks a provider per stage at dispatch time — a chain's later stages see fresh fleet state ( - ai-hub: the fabric secret gates the service HTTP surface — bearer on everything but /health and the ticketed peer path - vj: DREAM runs execute in the app — pipelines.rs becomes the run it used to watch (aicore §9 / F1) - asset-creator: the runner — generate one thing and put it in the catalog, one implementation for every surface (aicore - chat-ui: the session runs in the app — no broker anywhere on the chat path (aicore P8 / F5) - asset-store: assets.query is a first-class query endpoint — the bounded SQL surface outlives the broker (aicore P8 / F - asset-creator: CreatorTools — the chat tool pack for a store that only stores (aicore §9 / P8) - asset-store: the shrink — the store stores (aicore P7) - importer + asset-server host: the coordination era ends (aicore P7) - store config purge + asset-ui goes fleet-direct; the derive protocol gets its route proof (aicore P7) - client + chat dispatcher: the dead wire comes out (aicore P7/P8) - ai-hub: 0.3.0 — the health version says which era a node runs - ai-hub: the default fleet is 'gen' — apps hear the LAN without env plumbing - ai-hub: the preload note percents the prefill, not the job bar - ai-hub: conversations keep their KV — the wire mirror, the lane identity, the in-turn dynamic context (aicore §7) - ai-hub: an open-think model is thinking from its first token - libs: the zero-warning sweep — stitch casts say what they mean, xatlas keeps upstream's surface quietly - zero-warning sweep, round two — the first full-workspace pass - zero-warning sweep, round three — the model lanes and the deep examples - zero-warning sweep, round four — the last stragglers - zero-warning sweep, round five — vj and chat-ui - zero-warning sweep, round six — three cascades Co-authored-by: Claude <info@makepad.nl>
255 lines
5.5 KiB
TOML
255 lines
5.5 KiB
TOML
[package]
|
|
name = "makepad-diffusion"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
description = "Diffusion pipeline scaffolding for Makepad ggml backends"
|
|
license = "MIT"
|
|
|
|
[dependencies]
|
|
# Bake ggml-metal.metallib at build time (same as llama/tts). Without this
|
|
# the first Metal dispatch compiles the shader source at runtime.
|
|
makepad-ai-llm = { path = "../ai/llm" }
|
|
# Safetensors reader moved out of mlx (lane T2, /aiarch.md §1): mlx's other
|
|
# ~89k LOC (chat/KV, qwen35moe, ...) has no consumers here. mlx itself stays
|
|
# in the tree unbuilt until lane T3 deletes it.
|
|
makepad-ai-loader = { path = "../ai/loader" }
|
|
# DiffusionError/Result + the plain sharded-safetensors reader moved out to
|
|
# the ai model workspace (lane T6a, /aiarch.md §1) so the family crates that
|
|
# split out of this one later can share them without depending on all of
|
|
# diffusion.
|
|
makepad-ai-common = { path = "../ai/models/common" }
|
|
makepad-ai-h3 = { path = "../ai/models/h3" }
|
|
makepad-ai-flux = { path = "../ai/models/flux" }
|
|
makepad-ai-vision = { path = "../ai/models/vision" }
|
|
makepad-ai-rig = { path = "../ai/models/rig" }
|
|
makepad-ai-motion = { path = "../ai/models/motion" }
|
|
makepad-ai-sfx = { path = "../ai/models/sfx" }
|
|
makepad-ai-music = { path = "../ai/models/music" }
|
|
makepad-ai-speech = { path = "../ai/models/speech" }
|
|
makepad-ai-trellis = { path = "../ai/models/trellis" }
|
|
makepad-gltf = { path = "../gltf" }
|
|
makepad-micro-serde = { path = "../micro_serde" }
|
|
makepad-zune-core = { path = "../zune/zune-core" }
|
|
makepad-zune-png = { path = "../zune/zune-png" }
|
|
|
|
[workspace]
|
|
|
|
[[bin]]
|
|
name = "flux-smoke"
|
|
path = "src/bin/flux_smoke.rs"
|
|
|
|
[[bin]]
|
|
name = "flux-tokenize"
|
|
path = "src/bin/flux_tokenize.rs"
|
|
|
|
[[bin]]
|
|
name = "flux-clip-smoke"
|
|
path = "src/bin/flux_clip_smoke.rs"
|
|
|
|
[[bin]]
|
|
name = "flux-t5-smoke"
|
|
path = "src/bin/flux_t5_smoke.rs"
|
|
|
|
[[bin]]
|
|
name = "flux-text-smoke"
|
|
path = "src/bin/flux_text_smoke.rs"
|
|
|
|
[[bin]]
|
|
name = "flux-transformer-smoke"
|
|
path = "src/bin/flux_transformer_smoke.rs"
|
|
|
|
[[bin]]
|
|
name = "flux-generate"
|
|
path = "src/bin/flux_generate.rs"
|
|
|
|
[[bin]]
|
|
name = "flux-warm-bench"
|
|
path = "src/bin/flux_warm_bench.rs"
|
|
|
|
[[bin]]
|
|
name = "flux-t5-stage-compare"
|
|
path = "src/bin/flux_t5_stage_compare.rs"
|
|
|
|
[[bin]]
|
|
name = "safetensors-query"
|
|
path = "src/bin/safetensors_query.rs"
|
|
|
|
[[bin]]
|
|
name = "h3-validate"
|
|
path = "src/bin/h3_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "h3-vae-validate"
|
|
path = "src/bin/h3_vae_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "h3-generate"
|
|
path = "src/bin/h3_generate.rs"
|
|
|
|
[[bin]]
|
|
name = "h3-tokenize"
|
|
path = "src/bin/h3_tokenize.rs"
|
|
|
|
[[bin]]
|
|
name = "h3-audio-validate"
|
|
path = "src/bin/h3_audio_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "h3-vision-validate"
|
|
path = "src/bin/h3_vision_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "h3-vae-encode-validate"
|
|
path = "src/bin/h3_vae_encode_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "sa3-validate"
|
|
path = "src/bin/sa3_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "moss-validate"
|
|
path = "src/bin/moss_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "moss-generate"
|
|
path = "src/bin/moss_generate.rs"
|
|
|
|
[[bin]]
|
|
name = "trellis-validate"
|
|
path = "src/bin/trellis_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "sa3-generate"
|
|
path = "src/bin/sa3_generate.rs"
|
|
|
|
[[bin]]
|
|
name = "sa3-bake"
|
|
path = "src/bin/sa3_bake.rs"
|
|
|
|
[[bin]]
|
|
name = "trellis-generate"
|
|
path = "src/bin/trellis_generate.rs"
|
|
|
|
[[bin]]
|
|
name = "woosh-validate"
|
|
path = "src/bin/woosh_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "woosh-generate"
|
|
path = "src/bin/woosh_generate.rs"
|
|
|
|
[[bin]]
|
|
name = "indextts-w2v-validate"
|
|
path = "src/bin/indextts_w2v_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "indextts-gpt-validate"
|
|
path = "src/bin/indextts_gpt_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "indextts-s2mel-validate"
|
|
path = "src/bin/indextts_s2mel_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "indextts-bigvgan-validate"
|
|
path = "src/bin/indextts_bigvgan_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "hy-motion-checkpoint"
|
|
path = "src/bin/hy_motion_checkpoint.rs"
|
|
|
|
[[bin]]
|
|
name = "hy-motion-validate"
|
|
path = "src/bin/hy_motion_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "hy-motion-text-validate"
|
|
path = "src/bin/hy_motion_text_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "hy-motion-clip-validate"
|
|
path = "src/bin/hy_motion_clip_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "hy-motion-decode-validate"
|
|
path = "src/bin/hy_motion_decode_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "hy-motion-pipeline-validate"
|
|
path = "src/bin/hy_motion_pipeline_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "skin-tokens-validate"
|
|
path = "src/bin/skin_tokens_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "skin-tokens-qwen-validate"
|
|
path = "src/bin/skin_tokens_qwen_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "skin-tokens-beam-ops-validate"
|
|
path = "src/bin/skin_tokens_beam_ops_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "skin-tokens-output-validate"
|
|
path = "src/bin/skin_tokens_output_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "birefnet-validate"
|
|
path = "src/bin/birefnet_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "realesrgan-validate"
|
|
path = "src/bin/realesrgan_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "da3-validate"
|
|
path = "src/bin/da3_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "sam3-validate"
|
|
path = "src/bin/sam3_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "flux2-check-te"
|
|
path = "src/bin/flux2_check_te.rs"
|
|
|
|
[[bin]]
|
|
name = "flux2-edit-validate"
|
|
path = "src/bin/flux2_edit_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "flux2-dev-validate"
|
|
path = "src/bin/flux2_dev_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "h3-gguf-validate"
|
|
path = "src/bin/h3_gguf_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "flux-gguf-inspect"
|
|
path = "src/bin/flux_gguf_inspect.rs"
|
|
|
|
[[bin]]
|
|
name = "music3-validate"
|
|
path = "src/bin/music3_validate.rs"
|
|
|
|
[[bin]]
|
|
name = "music3-gguf-inspect"
|
|
path = "src/bin/music3_gguf_inspect.rs"
|
|
|
|
[[bin]]
|
|
name = "music3-gguf-generate"
|
|
path = "src/bin/music3_gguf_generate.rs"
|
|
|
|
[[bin]]
|
|
name = "music3-generate"
|
|
path = "src/bin/music3_generate.rs"
|
|
|
|
[[bin]]
|
|
name = "music3-native-bench"
|
|
path = "src/bin/music3_generate.rs"
|
|
|
|
[[bin]]
|
|
name = "ace-validate"
|
|
path = "src/bin/ace_validate.rs"
|