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

[gateway] Align /v1/loads and /model_info with sglang server; drop dead /rerank (#24167)

Browse Source 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Kangyan-Zhou
2026-05-02 11:43:30 -07:00
committed by GitHub
co-authored by Claude Opus 4.7
parent e0474fdd9b
commit d74d9bda49
6 changed files with 10 additions and 275 deletions
Download Patch File Download Diff File Expand all files Collapse all files
sgl-model-gateway/tests/routing/test_pd_routing.rs
+2 -2
View File
@@ -767,12 +767,12 @@ mod pd_routing_unit_tests {
("/health_generate", "GET", true), // Note: Python uses POST, we use GET
("/server_info", "GET", true),
("/v1/models", "GET", true),
("/get_model_info", "GET", true),
("/model_info", "GET", true),
("/generate", "POST", true),
("/v1/chat/completions", "POST", true),
("/v1/completions", "POST", true),
("/flush_cache", "POST", true),
("/get_loads", "GET", true),
("/v1/loads", "GET", true),
("/register", "POST", false), // NOT IMPLEMENTED - needs dynamic worker management
];