Commit graph

51 commits

Author SHA1 Message Date
sirius0xdev
b3fdb91e13
Update rtx6000-vllm.yaml 2026-05-23 00:47:34 -04:00
sirius0xdev
87c22e71a4
Update rtx6000-vllm.yaml 2026-05-22 23:45:57 -04:00
sirius0xdev
fa6dd3c8a6
Update rtx6000-vllm.yaml 2026-05-22 23:39:27 -04:00
sirius0xdev
54267b0818
Update rtx6000-vllm.yaml 2026-05-22 23:27:18 -04:00
sirius0xdev
6df297086c
Update rtx6000-vllm.yaml 2026-05-22 13:56:53 -04:00
sirius0xdev
3c542b2d41
Update rtx6000-vllm.yaml 2026-05-22 13:54:20 -04:00
sirius0xdev
af4cb3d321
Update rtx6000-vllm.yaml 2026-05-17 16:42:06 -04:00
sirius0xdev
1a6dd51076
Update rtx6000-vllm.yaml 2026-05-16 23:11:34 -04:00
sirius0xdev
aa1f5be323
Update rtx6000-vllm.yaml 2026-05-16 23:10:18 -04:00
sirius0xdev
18aa779232
Update rtx6000-vllm.yaml 2026-05-16 23:01:39 -04:00
sirius0xdev
0899aa1b97
Update rtx6000-vllm.yaml 2026-05-16 22:59:03 -04:00
sirius0xdev
3836578bb8
Update rtx6000-vllm.yaml 2026-05-16 22:58:38 -04:00
sirius0xdev
728a2dfe77
Update rtx6000-vllm.yaml 2026-05-16 22:57:54 -04:00
sirius0xdev
e4ce253e80
Update rtx6000-vllm.yaml 2026-05-16 22:35:02 -04:00
sirius0xdev
cfedb963e5 dial in vllm 2026-05-10 03:02:51 +00:00
sirius0xdev
4e2b0974f4 enforce eager set 2026-05-10 02:25:26 +00:00
sirius0xdev
ad30b9524f numseq lower 2026-05-10 02:20:42 +00:00
sirius0xdev
a718acffa6 lower num seq 2026-05-10 02:15:27 +00:00
sirius0xdev
52f1af7e73 fix vllm 2026-05-10 02:08:33 +00:00
sirius0xdev
bce6e18f2b fix vllm and tini 2026-05-10 01:48:34 +00:00
sirius0xdev
3d3f0a5a1f change vllm settings 2026-05-10 01:33:47 +00:00
sirius0xdev
1f38305394 add rays new deployment and fix gateway 2026-05-08 04:27:47 +00:00
sirius0xdev
bb86f0fc3f fix cuddagraph issue 2026-05-06 02:08:48 +00:00
sirius0xdev
2102ea882f image hell 2026-05-06 01:57:29 +00:00
sirius0xdev
2b6fc11986 vllm image issue 2026-05-06 01:54:58 +00:00
sirius0xdev
e05e71d0fc vllm image error fix 2026-05-06 01:42:12 +00:00
sirius0xdev
2200006c41 fix vllm error 2026-05-06 01:31:45 +00:00
sirius0xdev
5247e6caee fix vllm deployment 2026-05-06 01:22:07 +00:00
sirius0xdev
b0e77ea84f fuck me 2026-05-06 01:18:24 +00:00
sirius0xdev
7410d84f57 fix vllm 2026-05-06 01:14:00 +00:00
sirius0xdev
94565b7c3b
Update rtx6000-vllm.yaml 2026-05-05 20:44:49 -04:00
sirius0xdev
882be08f17
Update rtx6000-vllm.yaml 2026-05-04 22:01:15 -04:00
sirius0xdev
16c8ebc41b
Update rtx6000-vllm.yaml 2026-05-04 21:59:35 -04:00
sirius0xdev
e0971380ad vllm deploy 2026-05-05 01:03:33 +00:00
sirius0xdev
680a16e4a8 try new vllm config 2026-05-04 21:53:08 +00:00
sirius0xdev
73f82dc57c
Update rtx6000-vllm.yaml 2026-05-04 15:11:43 -04:00
sirius0xdev
ed39dcf598 fix: replace non-existent TsProxy CRD with ProxyGroup
TsProxy is not a CRD shipped by the Tailscale operator (v1.96.x).
The operator provides: ProxyClass, ProxyGroup, ProxyGroupPolicy,
DNSConfig, Tailnet, Connector, and Recorder.

Replace TsProxy with ProxyGroup (type: ingress) and annotate
rtx6000-brain-service with tailscale.com/proxy-group to expose
the vLLM endpoint via MagicDNS at rtx6000-brain-0.<tailnet>.ts.net:8000.
2026-05-04 04:47:34 +00:00
sirius0xdev
31e5af495a
Update rtx6000-vllm.yaml 2026-05-02 11:06:22 -04:00
sirius0xdev
324c69faf9
Update rtx6000-vllm.yaml 2026-05-02 09:11:46 -04:00
sirius0xdev
9a7904c219
Update rtx6000-vllm.yaml 2026-05-02 08:36:04 -04:00
sirius0xdev
864cfd2cc9
Update rtx6000-vllm.yaml 2026-05-02 08:26:09 -04:00
sirius0xdev
08e9998019
Update rtx6000-vllm.yaml 2026-05-02 08:24:21 -04:00
sirius0xdev
17f46261e0
Update rtx6000-vllm.yaml 2026-04-29 11:21:02 -04:00
sirius0xdev
24fee8f4a2
Update rtx6000-vllm.yaml 2026-04-29 09:41:48 -04:00
sirius0xdev
dd34e21f76
Update rtx6000-vllm.yaml 2026-04-29 01:22:41 -04:00
sirius0xdev
d08bf5844a feat: optimize RTX6000 vLLM KEDA scaling
- Rename deployment to rtx6000-brain-vllm to match scaler target ref
- Set deployment replicas to 0 (KEDA controlled)
- Add pollingInterval: 10s and cooldownPeriod: 30s for faster response

This enables scale-to-zero when idle and quick scale-up on first request.

See https://github.com/sirius0xdev/gcloud-lab/tree/master/infrastructure%2Fgpus%2Fbase
2026-04-29 04:12:36 +00:00
sirius0xdev
5622e6c49c
Update rtx6000-vllm.yaml 2026-04-28 23:55:29 -04:00
sirius0xdev
7b33f57cab add storage class 2026-04-29 02:07:21 +00:00
sirius0xdev
79942eeb5e fix disk type 2026-04-29 00:04:47 +00:00
sirius0xdev
bb7dcd5651 fix node selector for 6000pro 2026-04-28 23:16:51 +00:00