Commit Graph
14 Commits
Author SHA1 Message Date
Sage 14e9c40a72 [Observability] Expose python/rust frontend identity in /server_info (#39993)
Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>
2026-09-21 23:32:52 +08:00
1f60ddef5d [PD] Introduce runtime role switching between prefill and decode (#28403)
Signed-off-by: huanglong <huanglong@linux.alibaba.com>
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
Co-authored-by: huanglong <huanglong@linux.alibaba.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: Huang Long <121648372+LLLL114@users.noreply.github.com>
2026-09-18 01:45:12 +08:00
raghothamandLianmin Zheng c0b8725f5a Fix /model_info serialization when a config value is a class (#39237)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
2026-09-14 17:10:44 -07:00
Cheng Wan f1a512c51c [Config] msgspec.Struct for the config tier (#38753) 2026-09-09 19:41:19 -07:00
sglang-botandsglang-bot 6252993afe chore: update CI test est_time values (#38238)
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
2026-09-06 17:49:41 -07:00
Cheng WanandClaude Opus 5 ef20fab38a config: the forwarding slots go; the dispatcher calls the family directly (#36792)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-28 10:26:29 -07:00
97ba99067d Publish per-scheduler load on a dedicated socket for load-aware routers (#34608)
Co-authored-by: Kangyan Zhou <zky314343421@gmail.com>
Co-authored-by: Zhangheng <hzh0425@apache.org>
2026-08-27 19:33:18 +08:00
Cheng Wan d7b144f64e config: publishing is the process entry's job (#36251) 2026-08-26 04:58:41 -07:00
Cheng Wan b3c8f0d923 config: one control-plane log for the process (#35028) 2026-08-17 16:19:00 -07:00
Cheng Wan c70c7d72a8 config: the readback and the resolving view say what they are (#35027) 2026-08-17 16:18:19 -07:00
Lianmin Zheng 4794b401d5 [Observability] Add startup, memory, and hybrid SWA diagnostics (#33375) 2026-08-04 12:50:09 -07:00
Cheng Wan 0b3e8bedd1 config: keep runtime hicache and weight-version updates off ServerArgs (#33336)
The scheduler's runtime HiCache attach/detach wrote its own ServerArgs so the
internal-state readback would show the change; that readback already reports
the resolved config, so the writes become get_context().override(...) and the
namespace readers see them too.

The tokenizer side is per-engine — several Engines can share one process — so
its control-plane updates (weight version, model path + load format, HiCache
attach/detach) stay with the manager instead of moving to the process-global
bags. TokenizerManager gains record_config_updates / config_value /
resolved_config_dict, and the readbacks that used to observe the instance write
(/server_info, /model_info, the HiCache status endpoint, the gRPC bridge) now
overlay those updates onto the startup config.

test_server_info's stub grew the real manager instead of a SimpleNamespace, so
the overlay it now exercises cannot drift from production.

Writer ratchet 26 -> 19.
2026-08-02 21:23:38 -07:00
Rain JiangandLianmin Zheng be1930133a Convert IPC dataclasses to msgspec.Struct with opt-in msgpack transport (#28688)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
2026-06-26 12:04:03 -07:00
Kangyan-ZhouandClaude Opus 4.7 085777210c feat(kv-events): expose structured KV-event publisher block on /server_info (#25844)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-23 01:59:45 +08:00