Commit Graph
478 Commits
Author SHA1 Message Date
Ken Simpson 9a92fe2ecb Add provider-aware workflow partitioning 2026-08-22 20:10:22 -07:00
Ken Simpson 3d067372c5 Fix llama.cpp shared library discovery on SSH 2026-08-22 19:34:49 -07:00
Ken Simpson 86c132798b Add multimodal GGUF execution on SSH 2026-08-22 19:18:42 -07:00
Ken Simpson 9bf105cf6d Revert "Split provider-constrained remote components"
This reverts commit 4da58239196bdf9aea4be0640f051492d7109d84.
2026-08-22 18:57:25 -07:00
Ken Simpson 33478a3589 Split provider-constrained remote components 2026-08-22 18:54:34 -07:00
Ken Simpson 5d6c13abe2 Add SSH GGUF LLM backend 2026-08-22 18:45:06 -07:00
Ken Simpson 535d4073c9 Resolve LLM memory before remote placement 2026-08-22 17:37:00 -07:00
Ken Simpson df5d7aa574 Stage LLM profiles on SSH workers 2026-08-22 17:20:16 -07:00
Ken Simpson 0e8070e422 Include ComfyUI entry modules in SSH workers 2026-08-22 16:43:22 -07:00
Ken Simpson 19232a9738 Add conservative remote memory admission 2026-08-22 16:22:37 -07:00
Ken Simpson 8c2911e2f8 Fix top-level SSH worker startup 2026-08-22 16:00:37 -07:00
Ken Simpson 83166aacdf Load BuildKit worker images into Docker 2026-08-22 15:53:36 -07:00
Ken Simpson 0dfa1cf3a7 Harden SSH worker bootstrap 2026-08-22 15:49:03 -07:00
Ken Simpson a7293a2cb1 Harden self-hosted scheduling and lifecycle 2026-08-22 15:32:57 -07:00
Ken Simpson 42cae2378d Add SSH Docker remote execution 2026-08-22 15:19:12 -07:00
Ken Simpson 37467f10f6 Add generic execution environment models 2026-08-22 14:58:59 -07:00
Ken Simpson 7bb2509903 Merge remote main and bump version to 0.3.5 2026-08-21 15:36:53 -07:00
Ken Simpson 82fb495905 Recover LLM VRAM after vLLM eviction 2026-08-21 13:47:52 -07:00
Ken Simpson 095ebd0af1 Highlight Modal work in containing subgraphs 2026-08-21 13:10:06 -07:00
Ken Simpson 492fcfa60b Fix LLM prewarm scope and Triton child telemetry 2026-08-20 19:52:41 -07:00
Ken Simpson 8b0dc851ef Track genuine Triton compile cache misses 2026-08-20 18:05:16 -07:00
Ken Simpson db3bf46b5a Avoid reloading mapped compile cache volumes 2026-08-20 17:12:18 -07:00
Ken Simpson e72d3a9eaa Read proxy metadata from V3 hidden context 2026-08-20 16:17:37 -07:00
Ken Simpson a6ce43eaa9 Fix queued prompt proxy isolation 2026-08-20 16:17:37 -07:00
Ken Simpson 4b387239b4 Fix overlapping Modal warmup contexts 2026-08-20 16:17:37 -07:00
Ken Simpson 6d524ae885 Document loader prewarm lookup race 2026-08-20 16:17:37 -07:00
Ken Simpson 8e4ee37fab Accelerate Modal model startup 2026-08-20 16:17:37 -07:00
Ken Simpson 186d98ea3f Keep Modal protocol validation off GPU 2026-08-20 16:17:37 -07:00
Ken Simpson c524109d13 Speculatively prewarm next Modal worker 2026-08-20 16:17:37 -07:00
Ken Simpson 54afff864a Avoid raw video transfer for terminal saves 2026-08-20 00:25:27 -07:00
Ken Simpson f070b310f1 Keep Comfy snapshots out of LLM phases 2026-08-19 23:29:54 -07:00
Ken Simpson f9d85c19f3 Rebind affinity after Modal protocol probes 2026-08-19 22:49:16 -07:00
Ken Simpson 4f5aeb1c98 Fix Modal progress panel palette reference 2026-08-19 22:40:40 -07:00
Ken Simpson 6fcafdec05 Preserve remote phases across local preview fanout 2026-08-19 22:36:18 -07:00
Ken Simpson cd4791431e Fix runtime Modal node module metadata 2026-08-19 22:30:03 -07:00
Ken Simpson f43cd37c79 Split remote continuations from local previews 2026-08-19 21:45:11 -07:00
Ken Simpson 093b2bdeec Run local previews alongside remote continuations 2026-08-19 20:48:18 -07:00
Ken Simpson c92af6a8c2 Retain remote workers across local workflow gaps 2026-08-19 20:06:58 -07:00
Ken Simpson 6a2cbbf191 Instrument remote result publication stalls 2026-08-19 16:07:21 -07:00
Ken Simpson a1f4cac7c1 Prevent sampler replay across local phase splits 2026-08-19 13:07:36 -07:00
Ken Simpson e9948b2e37 Merge local Modal placement warning styling 2026-08-19 12:30:27 -07:00
Ken Simpson e18ddc81ba Clarify local Modal placement warning 2026-08-19 12:24:09 -07:00
Ken Simpson 39701644fe Fix async Modal cache writes 2026-08-19 12:18:02 -07:00
Ken Simpson d20773d338 Add automatic vLLM mode promotion 2026-08-19 11:48:57 -07:00
Ken Simpson 0abf4d36fd Add cached vLLM throughput benchmarking 2026-08-19 11:20:00 -07:00
Ken Simpson dc0d21737f Accelerate Hugging Face downloads with Xet 2026-08-19 11:02:22 -07:00
Ken Simpson 5b70c91621 Add mlx-dspark local LLM acceleration 2026-08-19 10:55:53 -07:00
Ken Simpson 5e910ef272 Prevent disabled LLM nodes from launching Modal 2026-08-19 10:33:32 -07:00
Ken Simpson 255e17a861 Merge Apple Silicon local LLM inference
# Conflicts:
#	README.md
#	tests/test_modal_llm.py
2026-08-19 10:06:17 -07:00
Ken Simpson 77c253f547 Add Apple Silicon local LLM inference 2026-08-19 09:58:50 -07:00