Compare commits

...
3 Commits
Author SHA1 Message Date
rock 1f906e95d8 Merge pull request 'feat(gateway): route clef-flash to clef-serve' (#74) from tmp-clef-route into main
CI / CI (push) Successful in 3m48s
2026-10-30 06:06:47 +00:00
Admin Bot affb1caa63 feat(gateway): route clef-flash to clef-serve
CI / CI (pull_request) Successful in 2m16s
Restores the route removed when the model could not run. It runs now, on a different
runtime: SGLang needs v0.5.22+ which upstream publishes only on CUDA 13, and CUDA 13
dropped Volta kernels. clef-serve loads the same weights through plain transformers in
fp16, sharded over two V100s, and serves the model's own systemone() on /v1/systemone.

Weights measured at 17.75 GiB in BF16; fp16 costs the same bytes per parameter.
2026-10-29 23:06:32 -07:00
rock b9f469a92f Merge pull request 'fix(gateway): stop routing clef-flash, the model cannot run here' (#73) from tmp-clef-check into main
CI / CI (push) Successful in 3m17s
2026-10-28 17:30:52 +00:00
File diff suppressed because one or more lines are too long