sirius0xdev
|
bd09ea4958
|
fix oom
|
2026-04-21 03:03:59 +00:00 |
|
sirius0xdev
|
2207a8a5c7
|
model swith
|
2026-04-21 02:54:01 +00:00 |
|
sirius0xdev
|
ed9112eb19
|
fix image pprocessor error
|
2026-04-21 02:45:41 +00:00 |
|
sirius0xdev
|
d78090b69c
|
fix quantization error
|
2026-04-21 02:39:30 +00:00 |
|
sirius0xdev
|
956ae90794
|
change model
|
2026-04-21 02:35:17 +00:00 |
|
sirius0xdev
|
852c481a3d
|
tool_call_parser error
|
2026-04-21 02:09:31 +00:00 |
|
sirius0xdev
|
d5bb38ab47
|
fix version problem with vllm
|
2026-04-21 02:00:24 +00:00 |
|
sirius0xdev
|
25fc06accf
|
fix vllm error
|
2026-04-21 01:49:00 +00:00 |
|
sirius0xdev
|
d109eba378
|
Update kustomization.yaml
|
2026-04-20 20:23:05 -04:00 |
|
sirius0xdev
|
9b30c142c4
|
Merge pull request #49 from sirius0xdev/fix/revert-a100-crashloop
Fix A100 crashloop by cleaning up invalid vllm args
|
2026-04-20 19:47:56 -04:00 |
|
Sirius Claw
|
29f57b48a0
|
Fix A100 crashloop by cleaning up invalid vllm args
|
2026-04-20 23:45:43 +00:00 |
|
sirius0xdev
|
887f91ac69
|
Merge pull request #48 from sirius0xdev/feature/dolphin-awq-l4
Switch L4 vLLM to Dolphin Qwen2 7B AWQ for speed and uncensored compl…
|
2026-04-20 16:50:07 -04:00 |
|
Sirius Claw
|
e1cf661692
|
Switch L4 vLLM to Dolphin Qwen2 7B AWQ for speed and uncensored compliance
|
2026-04-20 20:47:30 +00:00 |
|
sirius0xdev
|
b4d4bd9841
|
Merge pull request #47 from sirius0xdev/feature/hermes-agent-deployment
Add Hermes Agent deployment to customer1 namespace
|
2026-04-20 16:11:07 -04:00 |
|
Sirius Claw
|
ca2f14f25b
|
Add Hermes Agent deployment to customer1 namespace
|
2026-04-20 19:20:15 +00:00 |
|
sirius0xdev
|
2f163fab36
|
Merge pull request #46 from sirius0xdev/feature/maximize-l4-context
Maximize L4 vLLM context window
|
2026-04-20 12:29:03 -04:00 |
|
sirius0xdev
|
bca7bdec5e
|
Merge pull request #44 from sirius0xdev/fix/vllm-version-and-parser
fix: pin vLLM to v0.9.1 and use pythonic tool call parser
|
2026-04-20 12:28:51 -04:00 |
|
Sirius Claw
|
fb951600d7
|
chore: maximize vllm max_model_len on L4 to 32768
|
2026-04-20 16:14:27 +00:00 |
|
sirius0xdev
|
e146d618b8
|
Merge pull request #45 from sirius0xdev/docs/update-readme-architecture
docs: update README to reflect dual-tier PAaaS architecture and News Bot pipeline
|
2026-04-20 03:45:03 -04:00 |
|
Sirius Claw
|
399d1a58ed
|
docs: update README to reflect dual-tier PAaaS architecture and News Bot pipeline
|
2026-04-20 07:43:50 +00:00 |
|
Sirius Claw
|
687d61f626
|
fix: pin vLLM to v0.9.1 and use pythonic tool call parser
|
2026-04-20 07:23:43 +00:00 |
|
sirius0xdev
|
bab9d4863e
|
Merge pull request #43 from sirius0xdev/fix/revert-vllm-latest
fix: revert vLLM image to latest to support bleeding edge tool parsers
|
2026-04-20 03:22:48 -04:00 |
|
Sirius Claw
|
baa88975b5
|
fix: revert vLLM image to latest to support qwen3_coder tool parser
|
2026-04-20 07:16:42 +00:00 |
|
sirius0xdev
|
ec5eecf723
|
Merge pull request #42 from sirius0xdev/fix/vllm-tool-args-version
fix: bump pinned vLLM version to support tool calling arguments
|
2026-04-20 03:03:52 -04:00 |
|
Sirius Claw
|
35dc7f01ac
|
fix: bump pinned vLLM version to v0.7.3 to support tool calling arguments
|
2026-04-20 06:58:13 +00:00 |
|
sirius0xdev
|
5847b6b393
|
Merge pull request #40 from sirius0xdev/fix/kustomize-structure
fix: move paaas-landing to staging kustomization to follow component pattern
|
2026-04-20 02:29:46 -04:00 |
|
Sirius Claw
|
2e81e9fd8b
|
fix: move paaas-landing to staging kustomization to follow component pattern
|
2026-04-20 06:27:47 +00:00 |
|
sirius0xdev
|
32731edfc8
|
Merge pull request #39 from sirius0xdev/feat/add-paaas-landing-deployment
feat: add PAaaS landing page deployment
|
2026-04-20 02:13:51 -04:00 |
|
Sirius Claw
|
0e0cc508db
|
feat: add PAaaS landing page deployment
|
2026-04-20 06:09:50 +00:00 |
|
sirius0xdev
|
70ad49f21f
|
Merge pull request #38 from sirius0xdev/feat/optimize-vllm-cost-perf
feat: optimize cost via L4 spot instances and vLLM performance tuning
|
2026-04-20 01:39:35 -04:00 |
|
Sirius Claw
|
43eb51d5b7
|
feat: optimize cost via L4 spot instances and vLLM performance tuning
|
2026-04-20 05:38:36 +00:00 |
|
sirius0xdev
|
12aef25aa0
|
Merge pull request #37 from sirius0xdev/fix-l4-gpu-drivers
fix: sync L4 GPU nodepool, deployment, and drivers
|
2026-04-20 01:14:38 -04:00 |
|
Sirius Claw
|
7d34b3f649
|
fix: match vllm-l4 deployment nodeSelector and tolerations to nodepool labels/taints
|
2026-04-20 05:11:55 +00:00 |
|
Sirius Claw
|
0ab2305c1c
|
chore: remove trading scripts from infra repo
|
2026-04-20 04:53:22 +00:00 |
|
sirius0xdev
|
c6f186d106
|
Merge pull request #30 from sirius0xdev/feat-api-gateway-roadmap
docs: Add project ROADMAP.md
|
2026-04-20 00:51:20 -04:00 |
|
sirius0xdev
|
2134824757
|
Merge pull request #35 from sirius0xdev/fix-g4-l4-taint
fix: Match exact taint value for the L4 G2 nodepool
|
2026-04-20 00:50:59 -04:00 |
|
Sirius Claw
|
bf57982e2f
|
fix: make L4 nodepool 24/7 base and add missing gpu_driver_installation_config
|
2026-04-20 04:48:47 +00:00 |
|
Sirius Claw
|
5100d2732b
|
feat: Add Sirius Mean Reversion Pine Script
|
2026-04-20 04:39:49 +00:00 |
|
Sirius Claw
|
9173c3395d
|
fix: Update L4 tolerations to exact match the G2 nodepool taint
|
2026-04-20 04:39:01 +00:00 |
|
sirius0xdev
|
d0ffbad5e9
|
Merge pull request #34 from sirius0xdev/fix-keda-api-versions
fix: Update KEDA Helm controllers to Flux v2 APIs
|
2026-04-20 00:01:16 -04:00 |
|
Sirius Claw
|
4fb80d3157
|
fix: update KEDA Helm controllers to Flux v2 APIs
|
2026-04-20 04:00:10 +00:00 |
|
sirius0xdev
|
24f916fcec
|
Merge pull request #33 from sirius0xdev/feat-keda-controllers
feat: Add KEDA and HTTP Add-on controllers
|
2026-04-19 23:40:13 -04:00 |
|
Sirius Claw
|
e736d5f874
|
feat: Add KEDA and KEDA HTTP Add-on controllers
|
2026-04-20 03:36:34 +00:00 |
|
sirius0xdev
|
cc6dbd025a
|
Merge pull request #32 from sirius0xdev/config-point-to-l4
chore: point OpenClaw to the new L4 vLLM dispatcher
|
2026-04-19 23:31:42 -04:00 |
|
Sirius Claw
|
83efcbf745
|
chore: point OpenClaw to the new L4 vLLM dispatcher
|
2026-04-20 03:14:10 +00:00 |
|
sirius0xdev
|
34b17f77b0
|
Merge pull request #28 from sirius0xdev/feat-l4-and-keda
feat: Add L4 vLLM deployment and KEDA scale-to-zero for A100
|
2026-04-19 23:13:28 -04:00 |
|
Sirius Claw
|
7075b6d79d
|
docs: Add ROADMAP.md for API gateway and multi-tenant SaaS transition
|
2026-04-20 02:36:06 +00:00 |
|
Sirius Claw
|
8041f71063
|
feat: Switch L4 deployment to Qwen2.5-Coder-7B-Instruct-heretic
|
2026-04-20 02:32:01 +00:00 |
|
sirius0xdev
|
439ba8ab23
|
Merge pull request #29 from sirius0xdev/docs-ai-architecture
docs: Add AI architecture overview
|
2026-04-19 22:30:04 -04:00 |
|
sirius0xdev
|
ea8ea2801d
|
Merge pull request #27 from sirius0xdev/optimize-vllm-a100
chore: Optimize vLLM for A100 by removing artificial batch limits
|
2026-04-19 22:29:24 -04:00 |
|