Isotr0py b952f4d3c3 [v1] Add PrefixLM support to FlexAttention backend (#27938) ...

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

2025-12-07 15:51:36 +00:00

..

gpu

[Model Runner V2] Support min-p sampling (#30171)

2025-12-05 21:42:47 -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

[BugFix] Fix DBO assert assert B_block_table == B_q (#29933)

2025-12-04 14:48:54 -05:00

ec_connector_model_runner_mixin.py

[Doc]: fixing typos in multiple files. (#29685)

2025-11-28 08:41:41 -08:00

gpu_input_batch.py

[Model][6/N] Improve all pooling task | Support chunked prefill with ALL pooling (#27145)

2025-12-04 13:44:15 +00:00

gpu_model_runner.py

[v1] Add PrefixLM support to FlexAttention backend (#27938)

2025-12-07 15:51:36 +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

[Compile] Conditional compilation. Introduce compile_ranges (#24252)

2025-12-05 18:17:32 +00:00

kv_connector_model_runner_mixin.py

[Attention] Remove imports from vllm/attention/__init__.py (#29342)

2025-11-26 10:53:15 -07:00

lora_model_runner_mixin.py

[LoRA] Cleanup LoRA unused code (#29611)

2025-11-28 22:52:58 -08:00

tpu_input_batch.py

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

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

tpu_model_runner.py

Revert "[Renderer] Separate out RendererConfig from ModelConfig (#30145)" (#30199)

2025-12-07 00:00:22 -08:00

tpu_worker.py

[TPU] add tpu_inference (#27277)

2025-11-26 14:46:36 -08:00

ubatch_utils.py

[BugFix] Fix DBO assert assert B_block_table == B_q (#29933)

2025-12-04 14:48:54 -05:00

ubatching.py

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

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

utils.py

Revert "[Renderer] Separate out RendererConfig from ModelConfig (#30145)" (#30199)

2025-12-07 00:00:22 -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

Make PyTorch profiler gzip and CUDA time dump configurable (#29568)

2025-12-01 04:30:46 +00:00