Benjamin Chislett b7433ca1a4 [Spec Decode] Efficient padded speculation (#24539) ...

Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>

2025-09-18 01:07:24 -04:00

..

__init__.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

block_table.py

[Core] Use CpuGpuBuffer for block table tensors (#24795)

2025-09-16 19:18:06 -07:00

cpu_model_runner.py

[Bugfix] Fix Stream usage in CPU model runner and OneDNN kernel check (#25046)

2025-09-17 05:54:02 -07:00

cpu_worker.py

[Bugfix] Fix sequence parallelism bug when enable pipeline parallelism (#24021)

2025-09-16 04:32:32 +00:00

gpu_input_batch.py

[Spec Decode] Efficient padded speculation (#24539)

2025-09-18 01:07:24 -04:00

gpu_model_runner.py

[Spec Decode] Efficient padded speculation (#24539)

2025-09-18 01:07:24 -04:00

gpu_ubatch_wrapper.py

[Core/DBO][1/N] Add Dual-Batch Overlap mechanism to VLLM (#23693)

2025-09-16 12:21:48 -04:00

gpu_worker.py

[Bugfix] Fix sequence parallelism bug when enable pipeline parallelism (#24021)

2025-09-16 04:32:32 +00:00

kv_connector_model_runner_mixin.py

[BugFix] Fix pipeline parallel (#24621)

2025-09-10 23:05:30 -07:00

lora_model_runner_mixin.py

[Bugfix] Fix GPUModelRunner has no attribute lora_manager (#24762)

2025-09-12 23:55:14 -07:00

tpu_input_batch.py

[Doc]: fix typos in various files (#24726)

2025-09-12 06:43:12 -07:00

tpu_model_runner.py

[Multimodal] Remove legacy multimodal fields in favor of MultiModalFeatureSpec (#24548)

2025-09-12 21:42:23 +08:00

tpu_worker.py

[P/D] Add a shutdown method to the Connector API (#22699)

2025-09-07 23:07:00 -07:00

ubatch_splitting.py

[Core/DBO][1/N] Add Dual-Batch Overlap mechanism to VLLM (#23693)

2025-09-16 12:21:48 -04:00

ubatch_utils.py

[Core/DBO][1/N] Add Dual-Batch Overlap mechanism to VLLM (#23693)

2025-09-16 12:21:48 -04:00

ubatching.py

[Core/DBO][1/N] Add Dual-Batch Overlap mechanism to VLLM (#23693)

2025-09-16 12:21:48 -04:00

utils.py

[XPU] Whisper model support on XPU Platform (#25123)

2025-09-18 04:30:10 +00:00

worker_base.py

[Docs] Fix warnings in mkdocs build (continued) (#23743)

2025-08-27 17:17:29 +00:00

xpu_model_runner.py

[XPU] Fix xpu model runner call torch.cuda APIs (#25011)

2025-09-17 06:45:25 +00:00

xpu_worker.py

[Doc]: fix typos in Python comments (#24115)

2025-09-02 21:14:07 -07:00