Commit Graph
230 Commits
Author SHA1 Message Date
Ken Simpson 9a92fe2ecb Add provider-aware workflow partitioning 2026-08-22 20:10:22 -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 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 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 f9d85c19f3 Rebind affinity after Modal protocol probes 2026-08-19 22:49:16 -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 936c97b1f1 Silence successful Modal billing refreshes 2026-08-19 12:34:24 -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 f3cc47f987 Fix Modal billing across app redeployments 2026-08-19 09:26:21 -07:00
Ken Simpson 082909062b Stream Modal LLM progress and vLLM tokens 2026-08-19 09:09:12 -07:00
Ken Simpson 03a08e00ec Show hourly Modal app billing in status pill 2026-08-19 08:26:43 -07:00
Ken Simpson c631996ca8 Reconcile runtime pins before vLLM install 2026-08-19 08:10:08 -07:00
Ken Simpson 7a2028eecd Install vLLM on every Modal GPU image 2026-08-19 08:05:38 -07:00
Ken Simpson 28c4b42076 Avoid FlashInfer sampler JIT on Modal workers 2026-08-18 23:22:37 -07:00
Ken Simpson cb8f816963 Add co-resident vLLM backend for B300 2026-08-18 22:36:19 -07:00
Ken Simpson 54aeabd6e0 Preserve isolated live Modal canary settings 2026-08-18 21:25:39 -07:00
Ken Simpson 9a4fd944ac Add resident multimodal Modal LLM node 2026-08-18 21:22:08 -07:00
Ken Simpson f9f3bca2fe Inject named Modal secrets into remote workers 2026-08-18 14:20:09 -07:00
Ken Simpson 0cdec8be5a Support ComfyUI node replacements remotely 2026-08-17 21:53:29 -07:00
Ken Simpson 7f6775e5b4 Align ComfyUI support package pins 2026-08-17 20:56:16 -07:00
Ken Simpson f0a341ea07 Preserve singleton mapped image batches 2026-08-15 09:09:29 -07:00
Ken Simpson 728a56e337 Propagate mapped list metadata across components 2026-08-14 14:26:31 -07:00
Ken Simpson 9ba54bcc4c Fix heterogeneous mapped latent outputs 2026-08-14 10:23:43 -07:00
Ken Simpson d86bc9963f Install current ComfyUI core dependencies remotely 2026-08-13 21:23:01 -07:00
Ken Simpson b9d25ec3d4 Show estimated Modal GPU cost during execution 2026-08-13 20:22:36 -07:00
Ken Simpson 67179df97f Fix Modal status polling across event loops 2026-08-13 19:58:39 -07:00
Ken Simpson 9f18670773 Support V3 Autogrow inputs in remote validation 2026-08-13 18:29:22 -07:00
Ken Simpson 7d8cb15ac9 Show Modal container status in workflow UI 2026-08-13 18:18:06 -07:00
Ken Simpson f0c04c41cf Ensure artifact-only Modal workflows execute 2026-08-13 15:31:12 -07:00
Ken Simpson fc03dafcb7 Default Modal workflows to RTX Pro 6000 2026-08-09 10:08:09 -07:00
Ken Simpson d9c31e693b Show selected GPU in Modal status 2026-08-09 08:20:43 -07:00
Ken Simpson 3da4d3727b Fix workflow GPU deployment selection 2026-08-08 22:28:33 -07:00
Ken Simpson 242e61b945 Add workflow GPU selection 2026-08-07 12:42:21 -07:00
Ken Simpson 03942cf0ff Preserve JSON-safe remote prompt metadata 2026-08-05 14:50:04 -07:00