 Alexander Korolev
|
48af96bc5d
kindling recipes: close the --speculative-config triple-quote on the content line (mimo shape) — a trailing newline before the closing hit a different code path and the engine received apostrophe-wrapped JSON (argparse 'cannot be converted to loads'); form now byte-identical to the working mimo recipes, argv validated in-image against the real vLLM
|
hai 1 mes |
|
Alexander Korolev
|
4c3f95d199
kindling recipes: fix doubled --speculative-config value (generator inserted the JSON twice; engine boot crashed with argparse 'cannot be converted' — caught by first e2e diag run)
|
hai 1 mes |
|
Alexander Korolev
|
e9a4ff28ef
kindling recipes: docker_image_dir=glm53-kindling (shared build context for all 3 TP variants)
|
hai 1 mes |
|
Alexander Korolev
|
71163f27e6
kindlingai glm-5.3-flash-gx10: vendor their stack (mode B — image+patches under our rendezvous) + 3 transcribed recipes (TP4/TP2/TP6): entrypoint exec-args + all 9 experimental overlay envs 1:1, per-TP mimics of their case block (pins 26/8/26 GiB, MML 524288/163840/524288, batched 16384/8192/16384), DFlash2 spec + AdaptiveK + tp6 padded checkpoint; build.sh bakes the 39 overlay files into the image (no per-node mounts)
|
hai 1 mes |
