Nagisa125 6764777f00 [Bugfix] Fix MTP support for lmhead_tensor_parallel_size (#3915) ...

### What this PR does / why we need it?
Fix the issue of MTP being enabled and setting
Imhead_tensor_parallel_size=16 causing the inference to hang.

- vLLM version: v0.11.0
- vLLM main:
83f478bb19

Signed-off-by: wyh145 <1987244901@qq.com>

2025-10-31 10:30:28 +08:00

..

attention

[Model][3/N] Refactor sfa into mla and remove deepseek_v3_2.py (#3769)

2025-10-30 17:06:38 +08:00

compilation

[feat]dcp pcp support aclgraph (#3731)

2025-10-27 09:58:23 +08:00

core

Upgrade to new vllm commit (#3719)

2025-10-25 15:36:32 +08:00

device_allocator

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

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

distributed

[bugfix]cancel tokenize for layerwise_proxy (#3914)

2025-10-30 23:54:46 +08:00

eplb

[CI]Fix oom of deepseek-eplb nigtly test. (#3884)

2025-10-30 10:18:07 +08:00

kv_offload

Upgrade to 0.11.1 newest vllm commit (#3762)

2025-10-28 14:55:03 +08:00

lora

[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

2025-10-24 16:55:08 +08:00

model_loader

Upgrade to new vllm commit (#3719)

2025-10-25 15:36:32 +08:00

models

[Model][3/N] Refactor sfa into mla and remove deepseek_v3_2.py (#3769)

2025-10-30 17:06:38 +08:00

ops

[Bugfix] Fix MTP support for lmhead_tensor_parallel_size (#3915)

2025-10-31 10:30:28 +08:00

patch

[Model][3/N] Refactor sfa into mla and remove deepseek_v3_2.py (#3769)

2025-10-30 17:06:38 +08:00

quantization

【Bugfix】bugfix for weight load of kimi-k2 (#3798)

2025-10-27 21:18:35 +08:00

sample

Upgrade to 0.11.1 newest vllm commit (#3762)

2025-10-28 14:55:03 +08:00

spec_decode

[FEAT] Refactor spec decode to support efficient padded speculation (#3528)

2025-10-30 16:53:05 +08:00

torchair

mfix bug when max_seqs=14 in mtp=2 scenario and raise error when cudagraph_capture_sizes can't be an integer multiple of uniform_decode_query_lentp (#3910)

2025-10-31 09:24:50 +08:00

worker

[Bugfix] Fix MTP support for lmhead_tensor_parallel_size (#3915)

2025-10-31 10:30:28 +08:00

__init__.py

[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

2025-10-24 16:55:08 +08:00

ascend_config.py

[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

2025-10-24 16:55:08 +08:00

ascend_forward_context.py

[Perf] Delete redundant operations in model_runner and forward_context (#3677)

2025-10-29 15:59:55 +08:00

cpu_binding.py

[main] support cpu binding (#3546)

2025-10-21 09:17:03 +08:00

envs.py

[main] remove dbo code (#3712)

2025-10-25 15:53:01 +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

mfix bug when max_seqs=14 in mtp=2 scenario and raise error when cudagraph_capture_sizes can't be an integer multiple of uniform_decode_query_lentp (#3910)

2025-10-31 09:24:50 +08:00

utils.py

mfix bug when max_seqs=14 in mtp=2 scenario and raise error when cudagraph_capture_sizes can't be an integer multiple of uniform_decode_query_lentp (#3910)

2025-10-31 09:24:50 +08:00