lilinsiman 1705501ae2 [BugFix] Fix ACLgraph bug in Qwen3_32b_int8 case (#3204) ...

### What this PR does / why we need it?
1. Solved the issue where sizes capture failed for the Qwen3-32b-int8
model when aclgraph, dp1, and tp4 were enabled.
2. Added the exception thrown when sizes capture fails and provided a
solution
3. Add this common problem to the FAQ doc
### Does this PR introduce _any_ user-facing change?
no

### How was this patch tested?
ut

- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/releases/v0.11.0

Signed-off-by: lilinsiman <lilinsiman@gmail.com>

2025-09-28 17:44:04 +08:00

..

_templates/sections

[Doc] add v0.9.1 release note (#2646)

2025-09-03 18:04:27 +08:00

assets

[Doc] Support kimi-k2-w8a8 (#2162)

2025-08-06 19:28:47 +08:00

community

[Release] Add release note for v0.10.2rc1 (#2921)

2025-09-16 01:20:05 +08:00

developer_guide

[CI] Update vllm version to 20250922(5aeb925) (#3091)

2025-09-22 22:18:13 +08:00

locale/zh_CN/LC_MESSAGES

[Feature] Support moe multi-stream for aclgraph. (#2946)

2025-09-19 11:06:45 +08:00

logos

[Doc] Add sphinx build for vllm-ascend (#55)

2025-02-13 18:44:17 +08:00

tutorials

fix wrong --num-gpus parameter requirements, and avoid ambiguity (#3116)

2025-09-23 11:58:44 +08:00

user_guide

[main][quantization] Support deepseek w4a8 per-channel quantization (#3011)

2025-09-27 21:01:16 +08:00

conf.py

[Release] Add release note for v0.10.2rc1 (#2921)

2025-09-16 01:20:05 +08:00

faqs.md

[BugFix] Fix ACLgraph bug in Qwen3_32b_int8 case (#3204)

2025-09-28 17:44:04 +08:00

index.md

[Doc] Update user doc index (#1581)

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

installation.md

Revert "Upgrade CANN version to 8.3.rc1.alpha001 (#2903)" (#2909)

2025-09-13 16:21:54 +08:00

quick_start.md

[ReleaseNote] Release note of v0.10.0rc1 (#2225)

2025-08-07 14:46:49 +08:00