Chengji Yao 04e1642e32

[TPU] add kv cache update kernel (#19928) ...

Signed-off-by: Chengji Yao <chengjiyao@google.com>

2025-06-26 10:01:37 -07:00

..

core

[Core] feat: Implement Priority Scheduling in V1 Engine (#19057)

2025-06-22 20:18:08 -07:00

e2e

[CI] change spell checker from codespell to typos (#18711)

2025-06-11 19:57:10 -07:00

engine

[Bugfix] Allow CUDA_VISIBLE_DEVICES='' in Platform.device_id_to_physical_device_id (#18979)

2025-06-26 00:01:57 -07:00

entrypoints

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

kv_connector

[PD] Skip tp_size exchange with rank0 (#19413)

2025-06-25 20:04:39 -07:00

metrics

Fix ValueError: Missing value for tag key(s): model_name,engine. (#19113)

2025-06-04 17:10:45 +08:00

sample

[CI] change spell checker from codespell to typos (#18711)

2025-06-11 19:57:10 -07:00

shutdown

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

spec_decode

[Bugfix] Fix EAGLE vocab embedding construction for Llama 70B (#19033)

2025-06-05 19:10:08 -07:00

structured_output

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

tpu

[TPU] add kv cache update kernel (#19928)

2025-06-26 10:01:37 -07:00

worker

Export NaNs in logits to scheduler_stats if output is corrupted (#18777)

2025-06-20 22:47:16 +08:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

2024-11-11 23:05:38 +00:00

test_async_llm_dp.py

[Core] Raise when non-multi-instance DP clients target a DP rank (#19227)

2025-06-06 19:03:01 +08:00

test_metrics_reader.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_oracle.py

[Fix][V1] Remove --scheduling-policy oracle (#20010)

2025-06-24 09:52:15 -07:00

test_request.py

[Misc] Add __str__ for RequestStatus (#19780)

2025-06-18 03:03:01 +00:00

test_serial_utils.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

test_utils.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00