Commit Graph
20 Commits
Author SHA1 Message Date
Ken Simpson e679d068a6 Report accurate LLM staging progress 2026-08-25 16:30:14 -07:00
Ken Simpson 82fb495905 Recover LLM VRAM after vLLM eviction 2026-08-21 13:47:52 -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 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
Ken Simpson 082909062b Stream Modal LLM progress and vLLM tokens 2026-08-19 09:09:12 -07:00
Ken Simpson 240e188147 Separate Modal LLM reasoning output 2026-08-19 08:55:55 -07:00
Ken Simpson f2a23b2570 Record RTX PRO vLLM inference validation 2026-08-19 08:17:08 -07:00
Ken Simpson 7a2028eecd Install vLLM on every Modal GPU image 2026-08-19 08:05:38 -07:00
Ken Simpson fce72a3e1f Record live LLM and VAE co-residency 2026-08-19 00:11:07 -07:00
Ken Simpson a544cfa62c Document live generated-profile validation 2026-08-19 00:09:31 -07:00
Ken Simpson 0978444a28 Pin FlashAttention 3 for Qwen on B300 2026-08-18 23:49:05 -07:00
Ken Simpson bfb2343553 Use FlashAttention for B300 vLLM inference 2026-08-18 23:44:07 -07:00
Ken Simpson b0678d9593 Run Modal workers on Python 3.13 2026-08-18 23:31:04 -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 090231001b Resolve Hugging Face LLM profiles on CPU 2026-08-18 22:29:44 -07:00
Ken Simpson 9a4fd944ac Add resident multimodal Modal LLM node 2026-08-18 21:22:08 -07:00