cld2labs/sglang-gpt-oss - #113

Open

arpannookala-12 wants to merge 20 commits into

opea-project:mainfrom

cld2labs:cld2labs/sglang-gpt-oss

Commits on Jun 2, 2026

cld2labs/sglang-gpt-oss: add SGLang Helm chart for gpt-oss-20b on Xeon
arpannookala-12
committed
9fa50f0
cld2labs/sglang-gpt-oss: full patch stack for gpt-oss-20b on sglang Xeon CPU
arpannookala-12
committed
d549022
cld2labs/sglang-gpt-oss: add Phase 2 patches, canonical values, ApisixRoute templating
arpannookala-12
committed
e423fb0
cld2labs/sglang-gpt-oss: rewrite README in OPEA style + ignore local-only notes
arpannookala-12
committed
6334673
cld2labs/sglang-gpt-oss: refactor chart docs for model-agnostic framing
arpannookala-12
committed
04028ee
cld2labs/sglang-gpt-oss: add gpt-oss-20b model-deployment card + sglang troubleshooting
arpannookala-12
committed
7b53ad9
cld2labs/sglang-gpt-oss: drop Qwen3-8B default, require modelSource/modelName explicitly
arpannookala-12
committed
9870bbf
cld2labs/sglang-gpt-oss: move gpt-oss-20b values.yaml into the model-deployment dir
arpannookala-12
committed
8e4a32c
cld2labs/sglang-gpt-oss: close 2 doc gaps in gpt-oss-20b deployment.md
arpannookala-12
committed
6a284c0
cld2labs/sglang-gpt-oss: doc cleanup pass (Phase 1) — inline model flags, rewrite Step 1, repair appendix
arpannookala-12
committed
b66a58a
cld2labs/sglang-gpt-oss: bump chart default image.tag to fix11-debug
arpannookala-12
committed
8f20834
cld2labs/sglang-gpt-oss: drop dual-path framing; appendix bootstraps a cluster where generate-token.sh works
arpannookala-12
committed
35a7a58
cld2labs/sglang-gpt-oss: clarify appendix preamble — it produces an EI-shape cluster
arpannookala-12
committed
6f2e1ad
cld2labs/sglang-gpt-oss: build-and-import.sh autodetects nerdctl (kubeadm) vs k3s
arpannookala-12
committed
2cb87da
cld2labs/sglang-gpt-oss: install buildkit on-demand when running nerdctl path
arpannookala-12
committed
7158b5e
cld2labs/sglang-gpt-oss: pull buildkit from upstream GitHub release
arpannookala-12
committed
e6db49b
cld2labs/sglang-gpt-oss: stop hard-coding k3s in chart README + deployment.md
arpannookala-12
committed
7edd71e
cld2labs/sglang-gpt-oss: drop local-only .gitignore from chart dir
arpannookala-12
committed
1171136

Navigation Menu

cld2labs/sglang-gpt-oss - #113

cld2labs/sglang-gpt-oss#113
arpannookala-12 wants to merge 20 commits into
opea-project:mainfrom
cld2labs:cld2labs/sglang-gpt-oss

Commits on Jun 2, 2026

cld2labs/sglang-gpt-oss: add SGLang Helm chart for gpt-oss-20b on Xeon

cld2labs/sglang-gpt-oss: full patch stack for gpt-oss-20b on sglang Xeon CPU

cld2labs/sglang-gpt-oss: add Phase 2 patches, canonical values, ApisixRoute templating

cld2labs/sglang-gpt-oss: rewrite README in OPEA style + ignore local-only notes

cld2labs/sglang-gpt-oss: refactor chart docs for model-agnostic framing

cld2labs/sglang-gpt-oss: add gpt-oss-20b model-deployment card + sglang troubleshooting

cld2labs/sglang-gpt-oss: drop Qwen3-8B default, require modelSource/modelName explicitly

cld2labs/sglang-gpt-oss: move gpt-oss-20b values.yaml into the model-deployment dir

cld2labs/sglang-gpt-oss: close 2 doc gaps in gpt-oss-20b deployment.md

cld2labs/sglang-gpt-oss: doc cleanup pass (Phase 1) — inline model flags, rewrite Step 1, repair appendix

cld2labs/sglang-gpt-oss: bump chart default image.tag to fix11-debug

cld2labs/sglang-gpt-oss: drop dual-path framing; appendix bootstraps a cluster where generate-token.sh works

cld2labs/sglang-gpt-oss: clarify appendix preamble — it produces an EI-shape cluster

cld2labs/sglang-gpt-oss: build-and-import.sh autodetects nerdctl (kubeadm) vs k3s

cld2labs/sglang-gpt-oss: install buildkit on-demand when running nerdctl path

cld2labs/sglang-gpt-oss: pull buildkit from upstream GitHub release

cld2labs/sglang-gpt-oss: stop hard-coding k3s in chart README + deployment.md

cld2labs/sglang-gpt-oss: drop local-only .gitignore from chart dir

Commits on Jun 5, 2026

cld2labs/sglang-gpt-oss: bifurcate README into Scenario 1 (EI/Ansible) and Scenario 2 (k3s bootstrap)

cld2labs/sglang-gpt-oss: move APISIX timeout note to Step 5 in gpt-oss-20b deployment.md