homelab-frontend

riotpiao-poimen/homelab-frontend

Fork 0

...

Author	SHA1	Message	Date
Admin Bot	affb1caa63	feat(gateway): route clef-flash to clef-serve CI / CI (pull_request) Successful in 2m16s Details 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 Details	2026-10-28 17:30:52 +00:00
Admin Bot	9ff41e3131	fix(gateway): stop routing clef-flash, the model cannot run here CI / CI (pull_request) Successful in 2m7s Details The model list still pointed clef-flash at clef-flash-predictor. That predictor is gone: Clef needs SGLang v0.5.22+, published only on CUDA 13, and CUDA 13 dropped Volta kernels. Every GPU is a Tesla V100 (sm_70), so SGLang aborts with 'no kernel image is available'. SGLang's floor is sm75 regardless. Advertising it meant a caller would wait for a Service with no endpoints until its own timeout fired, instead of failing clearly. Remove the entry and keep the reasoning in its place, so restoring it later is a deliberate act tied to new hardware.	2026-10-28 10:30:30 -07:00

Author

SHA1

Message

Date

Admin Bot

affb1caa63

feat(gateway): route clef-flash to clef-serve

CI / CI (pull_request) Successful in 2m16s

Details

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

Details

2026-10-28 17:30:52 +00:00

Admin Bot

9ff41e3131

fix(gateway): stop routing clef-flash, the model cannot run here

CI / CI (pull_request) Successful in 2m7s

Details

The model list still pointed clef-flash at clef-flash-predictor. That predictor is gone:
Clef needs SGLang v0.5.22+, published only on CUDA 13, and CUDA 13 dropped Volta
kernels. Every GPU is a Tesla V100 (sm_70), so SGLang aborts with 'no kernel image is
available'. SGLang's floor is sm75 regardless.

Advertising it meant a caller would wait for a Service with no endpoints until its own
timeout fired, instead of failing clearly. Remove the entry and keep the reasoning in
its place, so restoring it later is a deliberate act tied to new hardware.

2026-10-28 10:30:30 -07:00

1 changed files with 1 additions and 1 deletions

k8s/gateway-config-secret.yaml

+1 -1

View File

File diff suppressed because one or more lines are too long

Compare commits