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

[Cleanup] Move mamba-max-states-per-path validation into _handle_mamba_backend (#32502)

Browse Source
This commit is contained in:
YAMY
2026-07-28 14:21:21 -07:00
committed by GitHub
parent b8b9f3c8f5
commit dd67452b4f
3 changed files with 9 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs_new/cookbook/autoregressive/Moonshotai/Kimi-K3.mdx
+1 -1
View File
@@ -36,7 +36,7 @@ If you do not want to use a Docker image, reproduce the dependency installation
Pick your hardware, then the deployment shape and operating point. Node count follows the hardware recipe (B200 2×8, GB200 4×4, H100 4×8, B300 1×8, H200 2×8, GB300 2×4, MI350X/MI355X 1×8), so it is not a separate choice.
**PD Mode** — `Unified` serves prefill and decode together. `Prefill` / `Decode` split them into dedicated pools (see [PD disaggregation](#pd-disaggregation)); `Prefill` ships two strategies on the TP8 platforms, both chunked at 16k: `Default` (TP8) and `Long-Context` (`--pp-size 8 --tp-size 1`, see [Deep PP](#deep-pp-for-long-context-prefill)).
**PD Mode** — `Unified` serves prefill and decode together. `Prefill` / `Decode` split them into dedicated pools (see [PD disaggregation](#3-4-pd-disaggregation)); `Prefill` ships two strategies on the TP8 platforms, both chunked at 16k: `Default` (TP8) and `Long-Context` (`--pp-size 8 --tp-size 1`, see [Deep PP](#deep-pp-for-long-context-prefill)).
**Strategy** — the operating point within that shape: