22dimensions 00e0243561 enable online serving quantization (#877) ...

For online serving, "ascend" quantization method is not a choice
natively, so we need to add "ascend" quantization method to quantization
methods list and the user can enable quantization using "vllm serve
--quantization ascend" command.

---------

Signed-off-by: 22dimensions <waitingwind@foxmail.com>

2025-05-17 17:36:04 +08:00

..

attention

[Bugfix][Model] Fix fusedmoe and make modelrunner_v1 compatible with latest vllm (#867)

2025-05-16 12:14:55 +08:00

core

[BugFix] Fix ascend scheduler bugs. (#822)

2025-05-12 21:15:17 +08:00

device_allocator

[MISC] Clean up torch_npu (#688)

2025-04-29 18:03:38 +08:00

distributed

[BugFix]add all2all when dp_size > 1 && downgrade npu_dequant_swiglu_quant (#819)

2025-05-15 09:19:55 +08:00

lora

[Bugfix] fix import error (#600)

2025-04-22 08:57:25 +08:00

models

[CI] Fix qwen2.5 vl CI failure (#888)

2025-05-17 05:13:32 +08:00

ops

[Bugfix][Model] Fix fusedmoe and make modelrunner_v1 compatible with latest vllm (#867)

2025-05-16 12:14:55 +08:00

patch

[BugFix]add all2all when dp_size > 1 && downgrade npu_dequant_swiglu_quant (#819)

2025-05-15 09:19:55 +08:00

quantization

enable online serving quantization (#877)

2025-05-17 17:36:04 +08:00

worker

[Bugfix][Model] Fix fusedmoe and make modelrunner_v1 compatible with latest vllm (#867)

2025-05-16 12:14:55 +08:00

__init__.py

[CI] Patch torch.library.infer_schema for fused moe ops to fix CI (#854)

2025-05-14 19:49:09 +08:00

envs.py

[Bugfix] Fix the method of importing environment variables in DeepSee… (#817)

2025-05-13 12:52:30 +08:00

platform.py

enable online serving quantization (#877)

2025-05-17 17:36:04 +08:00

utils.py

enable online serving quantization (#877)

2025-05-17 17:36:04 +08:00