Roger Wang c2c661af9b [Bugfix] Fix overallocation in MM profiling (#29386) ...

Signed-off-by: Roger Wang <hey@rogerw.io>

2025-11-25 12:38:36 +00:00

..

gpu

[Model Runner V2] Simplify Eagle bookkeeping with num_rejected (#29347)

2025-11-24 13:54:59 -08:00

__init__.py

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

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

block_table.py

[Bugfix] Fix block size in block_table with PCP (#29094)

2025-11-22 01:34:28 +00:00

cpu_model_runner.py

Replace torch.cuda.Event with torch.Event for better hardware compatibility (#26985)

2025-11-18 11:34:36 -08:00

cpu_worker.py

[CI] Fix mypy for vllm/v1/worker (#29037)

2025-11-21 11:36:07 +08:00

dp_utils.py

[Misc] Replace CUDA_VISIBLE_DEVICES in DP with torch.cuda.set_device for device selection on cuda-like devices (#27564)

2025-10-30 11:41:44 -04:00

ec_connector_model_runner_mixin.py

[Core] Encoder separation for Encode-Prefill-Decode Disaggregation (#25233)

2025-11-11 18:58:33 -08:00

gpu_input_batch.py

[Model] Add HunyuanOCR support (#29327)

2025-11-25 03:28:51 +00:00

gpu_model_runner.py

[Bugfix] Fix overallocation in MM profiling (#29386)

2025-11-25 12:38:36 +00:00

gpu_ubatch_wrapper.py

[CI] Fix mypy for vllm/v1/worker (#29037)

2025-11-21 11:36:07 +08:00

gpu_worker.py

GPU Model Runner V2 (#25266)

2025-11-21 08:20:55 -08:00

kv_connector_model_runner_mixin.py

[CI] Fix mypy for vllm/v1/worker (#29037)

2025-11-21 11:36:07 +08:00

lora_model_runner_mixin.py

[Bugfix][LoRA][Spec Decode] Support LoRA with speculative decoding (#21068)

2025-11-08 01:58:22 +00:00

tpu_input_batch.py

[BugFix] Fix chunked prompt logprobs + preemption (#29071)

2025-11-22 16:07:18 -05:00

tpu_model_runner.py

[BugFix] Fix chunked prompt logprobs + preemption (#29071)

2025-11-22 16:07:18 -05:00

tpu_worker.py

[Misc] Move dynamic seed initialization to EngineArgs (#29165)

2025-11-21 15:27:44 +00:00

ubatch_utils.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

ubatching.py

Replace torch.cuda.Event with torch.Event for better hardware compatibility (#26985)

2025-11-18 11:34:36 -08:00

utils.py

[CI] Fix mypy for vllm/v1/worker (#29037)

2025-11-21 11:36:07 +08:00

worker_base.py

[CI] Fix mypy for vllm/v1/worker (#29037)

2025-11-21 11:36:07 +08:00

xpu_model_runner.py

Replace torch.cuda.Event with torch.Event for better hardware compatibility (#26985)

2025-11-18 11:34:36 -08:00

xpu_worker.py

[CI] Fix mypy for vllm/v1/worker (#29037)

2025-11-21 11:36:07 +08:00