xuyexiong 30e3d86b0f Revert "[BUGFIX] Mtp torchair pd fix (#3449)" (#3500) ...

This reverts commit b0ae203e72d87985314d583e211dddca6f351958.

### What this PR does / why we need it?
The fix is not ready yet, conflict with #3411 need to revert first. Will
fix this issue later

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

Signed-off-by: xuyexiong <xuyexiong@huawei.com>

2025-10-17 09:42:48 +08:00

..

attention

[Feat]Qwen3 Moe supports npu_add_rms_norm_quant op by default, update op with bias, resolve conflict with weight prefetch (#3465)

2025-10-17 09:30:51 +08:00

compilation

[Feat]Qwen3 Moe supports npu_add_rms_norm_quant op by default, update op with bias, resolve conflict with weight prefetch (#3465)

2025-10-17 09:30:51 +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

[BugFix]GPQA Accuracy Issue Bugfix (#3476)

2025-10-15 23:28:17 +08:00

eplb

[EPLB]Record expert map without dynamic eplb. (#3409)

2025-10-15 14:21:15 +08:00

lora

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

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

models

[BugFix] fix qwenVL quant assertion error (#3466)

2025-10-16 17:08:00 +08:00

multistream

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

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

ops

[Feat]Qwen3 Moe supports npu_add_rms_norm_quant op by default, update op with bias, resolve conflict with weight prefetch (#3465)

2025-10-17 09:30:51 +08:00

patch

[Refactor] Adapt deepseek-v3.2 to vllm 0.11.0 (#3432)

2025-10-15 17:48:58 +08:00

quantization

[BugFix] fix qwenVL quant assertion error (#3466)

2025-10-16 17:08:00 +08:00

sample

Drop 0.10.2 (#3284)

2025-10-09 10:28:38 +08:00

spec_decode

[Refactor] Adapt deepseek-v3.2 to vllm 0.11.0 (#3432)

2025-10-15 17:48:58 +08:00

torchair

Revert "[BUGFIX] Mtp torchair pd fix (#3449)" (#3500)

2025-10-17 09:42:48 +08:00

worker

[Fix] Clears unused slot mappings and fix accuracy issue with MLA models when enabling FULL_DECODE_ONLY (#3482)

2025-10-16 19:43:09 +08:00

__init__.py

[Refactor] Adapt deepseek-v3.2 to vllm 0.11.0 (#3432)

2025-10-15 17:48:58 +08:00

ascend_config.py

[Refactor] Adapt deepseek-v3.2 to vllm 0.11.0 (#3432)

2025-10-15 17:48:58 +08:00

ascend_forward_context.py

[Feat]Qwen3 Moe supports npu_add_rms_norm_quant op by default, update op with bias, resolve conflict with weight prefetch (#3465)

2025-10-17 09:30:51 +08:00

envs.py

[Feat] Flash comm allgher ep (#3334)

2025-10-15 19:36:32 +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

[Feat] Flash comm allgher ep (#3334)

2025-10-15 19:36:32 +08:00

utils.py

[Feat]Qwen3 Moe supports npu_add_rms_norm_quant op by default, update op with bias, resolve conflict with weight prefetch (#3465)

2025-10-17 09:30:51 +08:00