[Doc] Tiny update dsv4 doc (#29827)
This commit is contained in:
@@ -32,7 +32,7 @@ For how to launch the image, see [Install → Method 3: Using Docker](../../../d
|
|||||||
|
|
||||||
**NVIDIA GPUs**
|
**NVIDIA GPUs**
|
||||||
|
|
||||||
A single image — `lmsysorg/sglang:latest` — covers the **datacenter GPUs** in this cookbook (B200 / B300 / GB200 / GB300 / H100 / H200). For **RTX PRO 6000 (SM120)**, use the nightly `lmsysorg/sglang:dev` instead — SM120 support isn't in `:latest` yet (see the RTX PRO 6000 note below).
|
A single image — `lmsysorg/sglang:latest` — covers the **datacenter GPUs** in this cookbook (B200 / B300 / GB200 / GB300 / H100 / H200 / RTX PRO 6000).
|
||||||
|
|
||||||
```bash Command
|
```bash Command
|
||||||
docker pull lmsysorg/sglang:latest
|
docker pull lmsysorg/sglang:latest
|
||||||
@@ -296,7 +296,7 @@ TCP, which can lead to garbled KV transfer on large checkpoints.
|
|||||||
RTX PRO 6000 (96 GB) runs **Flash only** — V4-Pro doesn't fit on 8× 96 GB. It uses the
|
RTX PRO 6000 (96 GB) runs **Flash only** — V4-Pro doesn't fit on 8× 96 GB. It uses the
|
||||||
**low-latency / TP-only** recipe (TP=4, single node) with the **Marlin** W4A16 MoE runner and
|
**low-latency / TP-only** recipe (TP=4, single node) with the **Marlin** W4A16 MoE runner and
|
||||||
`--mem-fraction-static 0.70`; the Deploy panel greys out the other recipes for this card.
|
`--mem-fraction-static 0.70`; the Deploy panel greys out the other recipes for this card.
|
||||||
HiCache and MegaMoE are **not** supported on RTX PRO 6000. For Docker, use the nightly `lmsysorg/sglang:dev` image — SM120 support isn't in `lmsysorg/sglang:latest` yet (the Deploy panel's Docker mode already points this card at `:dev`).
|
HiCache and MegaMoE are **not** supported on RTX PRO 6000.
|
||||||
|
|
||||||
**AMD (MI300X / MI355X) note**
|
**AMD (MI300X / MI355X) note**
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user