minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[Config] Retire get_global_server_args, and clear the deprecated flags that have a replacement (#38375)

Browse Source
This commit is contained in:
Cheng Wan
2026-09-08 16:42:12 -07:00
committed by GitHub
parent 5177a3ec08
commit db272201a2
213 changed files with 625 additions and 892 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude/skills/cookbook-add-model/references/authoring-reference.md
+1 -1
View File
@@ -178,7 +178,7 @@ schemas (full reference in the `_playground.jsx` header):
| `pdDisagg` | Mode + transfer backend (+ optional per-backend env via `envWhen` hw-gate) + IB device + optional `router{port, command}` | Model supports prefill/decode disaggregation. A `modes[]` entry may carry `flags` / `env` that only that role needs (`prefill`'s `--load-balance-method`, `decode`'s `--disaggregation-decode-polling-interval`, ...); they are emitted only while that role is selected, and a flag whose head the base cell already sets is replaced rather than duplicated. Put role-specific settings here, NOT in the cells — a cell carries one recipe, and the role is a Playground overlay. In `router.command` the ports MUST be `{{PREFILL_PORT}}` / `{{DECODE_PORT}}` / `{{ROUTER_PORT}}`: the engine substitutes them from its own `PD_PORTS` (prefill 30000, decode **30100**), so a literal port silently points the router at something the generated decode command never binds. When a PD role is active and `router` is set, the playground shows the router (SGLang Model Gateway) launch command as a companion block and retargets the cURL modal to `router.port`. |
| `hicache` | Enable + storage + write policy | Model is large enough that hierarchical KV cache matters. |
| `hisparse` | Enable + host-ratio select; whole card gated on the live PD-Disagg mode being `decode` | DSA-style model (DeepSeek-V3.2 / V4, GLM-5) that supports decode-side hierarchical sparse attention. |
| `flagSelects` | A config-declared **list** of single-selects, each `{ id, title, stripPrefixes, options }` (option = `{ id, label, flags?, hide?, disable?, disableReason? }`); a flagless option is the "none"/accuracy-safe choice | A titled single-select that picks one value of a flag family the other axes don't model — e.g. KV-cache dtype (`--kv-cache-dtype`), mamba scheduler strategy (`--mamba-scheduler-strategy`). Generic: no engine change to add another. |
| `flagSelects` | A config-declared **list** of single-selects, each `{ id, title, stripPrefixes, options }` (option = `{ id, label, flags?, hide?, disable?, disableReason? }`); a flagless option is the "none"/accuracy-safe choice | A titled single-select that picks one value of a flag family the other axes don't model — e.g. KV-cache dtype (`--kv-cache-dtype`), mamba scheduler strategy (`--mamba-radix-cache-strategy`). Generic: no engine change to add another. |
**Per-chip constraints**: any chip entry in any axis can be wrapped with
`hide` / `disable` constraint objects: