Mengqing Cao 050d202bb9 [Quickfix] Fix dp+ep+tp error when sp chunked the hidden_states (#3246) ...

### What this PR does / why we need it?
Fix dp+ep+tp inplace copy error when sp chunked the `hidden_states`.


### How was this patch tested?
test locally with the following scripts
```bash
python examples/offline_data_parallel.py \
        --model="Qwen/Qwen3-30B-A3B" \
        --dp-size=2 \
        --tp-size=2 \
        --enable-expert-parallel
```

Signed-off-by: MengqingCao <cmq0113@163.com>

2025-09-29 09:12:49 +08:00

..

attention

bugfix for mtp>1 (#3174)

2025-09-26 09:04:16 +08:00

compilation

[Refactor][Graph] Move graph parameter logic to acl_graph module (#3101)

2025-09-22 22:23:14 +08:00

core

[BugFix] Fix ascend scheduler assert error (#3191)

2025-09-28 18:22:08 +08:00

device_allocator

[Misc]Clean up useless import from vllm (#2049)

2025-07-28 16:01:59 +08:00

distributed

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

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

eplb

FlashLB algorithm (#3042)

2025-09-23 10:27:14 +08:00

lora

[Bugfix][LoRA] Fix forward error and shape mismatch when using LoRA (#3153)

2025-09-28 17:30:50 +08:00

models

[3/N][Refactor][Qwen3-Next] Refacotr model structure and fix bug by vllm #25400 (#3142)

2025-09-28 21:14:36 +08:00

multistream

[Quickfix] update CachedRequestState as NewRequestData changed (#2367)

2025-08-15 07:35:27 +08:00

ops

[Quickfix] Fix dp+ep+tp error when sp chunked the hidden_states (#3246)

2025-09-29 09:12:49 +08:00

patch

[CI] Upgrade vllm to newest commit (#3182)

2025-09-26 06:18:15 +08:00

quantization

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

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

sample

[CI] Upgrade vLLM to 20250920 (c60e613) and address config break (#3067)

2025-09-21 09:49:17 +08:00

spec_decode

[Eagle] Fix attn_mask index out of range in high concurrency situations (#3187)

2025-09-28 18:09:26 +08:00

torchair

[CI][Bugfix] Quickfix for DPMetaData (#3234)

2025-09-28 21:11:22 +08:00

worker

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

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

__init__.py

Bump torch version to 2.7.1 (#1562)

2025-08-05 08:43:24 +08:00

ascend_config.py

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

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

ascend_forward_context.py

[Refactor] [SP]The sequence parallelism characteristics in the MoE and Dense models are integrated into a single solution. (#3085)

2025-09-24 11:29:59 +08:00

envs.py

[core]vllm-ascend support msMonitor tool (#3123)

2025-09-25 14:15:02 +08:00

meta_registration.py

Fix the bugs about operator registration by PyTorch Dispatcher (#2786)

2025-09-13 11:58:52 +08:00

platform.py

[Quickfix] Fix dp+ep+tp error when sp chunked the hidden_states (#3246)

2025-09-29 09:12:49 +08:00

utils.py

[Model] Optimizing gemma3 model's GemmaRMSNorm function (#3151)

2025-09-28 21:19:10 +08:00