Nick Hill 094fcce250 [BugFix] Re-fix async multimodal cpu tensor race condition (#31373) ...

Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: njhill <nickhill123@gmail.com>

2025-12-28 03:05:08 -08:00

..

gpu

[Attention] Make seq_lens_cpu optional in CommonAttentionMetadata to enable true async spec-decode (#29624)

2025-12-09 17:18:10 -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

cp_utils.py

[Misc][PCP&DCP] relocate PCP feature check (#30050)

2025-12-11 03:36:18 -08:00

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

[Cleanup] Refactor profiling env vars into a CLI config (#29912)

2025-12-09 13:29:33 -05:00

dp_utils.py

[feature] extend DBO to XBO (#30120)

2025-12-16 00:04:01 -05:00

ec_connector_model_runner_mixin.py

[Chore] Remove unused noqas (#31263)

2025-12-24 05:38:46 -08:00

gpu_input_batch.py

[Cleanup] Remove unused ModelRunner V1 InputBatch.num_tokens field (#30218)

2025-12-18 09:17:00 -08:00

gpu_model_runner.py

[BugFix] Re-fix async multimodal cpu tensor race condition (#31373)

2025-12-28 03:05:08 -08:00

gpu_ubatch_wrapper.py

[feature] extend DBO to XBO (#30120)

2025-12-16 00:04:01 -05:00

gpu_worker.py

[Core][Hybrid allocator + connector] Support hybrid allocator + kv cache connector (#30166)

2025-12-26 18:25:46 -08:00

kv_connector_model_runner_mixin.py

[Chore] Remove unused noqas (#31263)

2025-12-24 05:38:46 -08:00

lora_model_runner_mixin.py

[Core] Initialize LoRA support for tower and connector in multi-modal models (#26674)

2025-12-26 04:48:20 -08:00

tpu_input_batch.py

[Cleanup] Remove unused ModelRunner V1 InputBatch.num_tokens field (#30218)

2025-12-18 09:17:00 -08:00

tpu_model_runner.py

[Core] Initialize LoRA support for tower and connector in multi-modal models (#26674)

2025-12-26 04:48:20 -08:00

tpu_worker.py

[Core][Hybrid allocator + connector] Support hybrid allocator + kv cache connector (#30166)

2025-12-26 18:25:46 -08:00

ubatch_utils.py

[feature] extend DBO to XBO (#30120)

2025-12-16 00:04:01 -05:00

ubatching.py

[feature] extend DBO to XBO (#30120)

2025-12-16 00:04:01 -05:00

utils.py

[Chore] Factor out logic for requesting initial memory (#30868)

2025-12-17 07:32:17 -08:00

worker_base.py

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

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

workspace.py

[BugFix] Fix memory spike in workspace allocation (#30744)

2025-12-16 06:46:22 -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

[Cleanup] Refactor profiling env vars into a CLI config (#29912)

2025-12-09 13:29:33 -05:00