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

..

attention

[CI] Upgrade vllm version - 0925 (#3167)

2025-09-25 14:20:10 +08:00

compilation

[Test]Add unit test for compilation/acl_graph.py (#3039)

2025-09-19 21:31:17 +08:00

core

[CORE] concurrent partial prefills (#2372)

2025-09-24 17:12:55 +08:00

device_allocator

add ut for device allocator/camem and mutistream/layers (#2037)

2025-07-31 19:17:27 +08:00

distributed

Dynamic Expert Load Balance with Zero-like-overhead (#2956)

2025-09-17 10:36:43 +08:00

eplb

[EPLB] ut for EPLB (#3035)

2025-09-24 17:14:38 +08:00

fake_weight

[CI] Add unit test framework (#1201)

2025-06-16 18:32:28 +08:00

kv_connector

[P/D][BugFix]Mooncake timeout release bug fix (#2899)

2025-09-24 11:22:46 +08:00

models

[CI] Upgrade vLLM version (#3139)

2025-09-25 07:36:51 +08:00

multistream

add ut for device allocator/camem and mutistream/layers (#2037)

2025-07-31 19:17:27 +08:00

ops

Remove qwen3 moe MC2 cumsum & cast (#3126)

2025-09-26 08:51:30 +08:00

patch/worker/patch_common

[feat]: oproj tensor parallelism in pure DP and graph-mode scenarios. (#2167)

2025-09-07 10:31:32 +08:00

quantization

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

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

sample

[main] add pd transfer for ascend scheduler (#2753)

2025-09-10 08:46:39 +08:00

torchair

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

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

worker

Revert "[Disagg][Perf] Use NPU event sync instead of blocking tolist (#3194)

2025-09-26 06:17:36 +08:00

__init__.py

[2/4][Refactor] Refactor torchair utils (#1892)

2025-07-21 19:43:30 +08:00

base.py

[Feature]: implement the fusion of allreduce and matmul in prefill phase when tp is enabled (#1926)

2025-07-28 15:13:37 +08:00

conftest.py

[1/N][CustomOp] Register activation customop instead of overwrite forward_oot (#1841)

2025-07-18 23:07:14 +08:00

test_ascend_config.py

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

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

test_envs.py

[Misc] Remove redundant imported envs, using envs_ascend instead (#2193)

2025-08-14 09:33:39 +08:00

test_platform.py

[refactor] refactor deepseek-related files (#2849)

2025-09-16 14:13:07 +08:00

test_utils.py

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

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