Wang Kunpeng e3a2443c3a [main][Doc] add mla pertoken quantization FAQ (#2018) ...

### What this PR does / why we need it?
When using deepseek series models generated by the --dynamic parameter,
if torchair graph mode is enabled, we should modify the configuration
file in the CANN package to prevent incorrect inference results.

- vLLM version: v0.10.0
- vLLM main:
7728dd77bb

---------

Signed-off-by: Wang Kunpeng <1289706727@qq.com>

2025-07-27 08:47:51 +08:00

..

images

[Doc] Update user doc index (#1581)

2025-07-10 14:26:59 +08:00

graph_mode.md

[Doc] Add qwen3 embedding 8b guide (#1734)

2025-07-11 17:40:17 +08:00

index.md

[Doc] Update user doc index (#1581)

2025-07-10 14:26:59 +08:00

lora.md

[Doc] Fix 404 error (#1797)

2025-07-15 11:52:38 +08:00

quantization.md

[main][Doc] add mla pertoken quantization FAQ (#2018)

2025-07-27 08:47:51 +08:00

sleep_mode.md

[1/2/N] Enable pymarkdown and python __init__ for lint system (#2011)

2025-07-25 22:16:10 +08:00

structured_output.md

[Doc] Update user doc index (#1581)

2025-07-10 14:26:59 +08:00