Harry Mellor 53c0fa1e25 Ensure that pid passed to kill_process_tree is int for mypy (#17051) ...

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2025-04-23 07:32:26 -07:00

..

attention

[BugFix] llama4 fa3 fix - RuntimeError: scheduler_metadata must have shape (metadata_size) (#16998)

2025-04-22 21:49:24 -07:00

core

[V1] Remove pre-allocation for KV cache (#16941)

2025-04-22 00:52:18 -07:00

engine

[V1] Avoid socket errors during shutdown when requests are in in-flight (#16807)

2025-04-23 12:36:29 +08:00

executor

[BugFix] Remove default multiproc executor collective_rpc timeout (#17000)

2025-04-22 23:27:14 +00:00

metrics

[V1] Remove log noise when idle (#16735)

2025-04-16 21:34:08 -07:00

sample

[TPU][V1] Enable Top-P (#16843)

2025-04-22 00:46:07 +00:00

spec_decode

[BugFix][Spec Decode] No in-place update to draft probs (#16952)

2025-04-21 19:54:19 -07:00

stats

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

structured_output

[V1][Structured Output] Move xgrammar related utils to backend_xgrammar.py (#16578)

2025-04-16 17:01:36 +08:00

worker

[Core][V1][TPU] Enable structured decoding on TPU V1 (#16499)

2025-04-22 18:05:23 -06:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

kv_cache_interface.py

[V1] Implement sliding window attention in kv_cache_manager (#14097)

2025-04-01 00:33:17 -07:00

outputs.py

[V1] Aggregate chunked prompt logprobs in model runner (#14875)

2025-03-24 12:27:57 -04:00

request.py

[Bugfix] Avoid transferring cached multi-modal items from P0 to P1 (#16273)

2025-04-09 00:51:27 -07:00

serial_utils.py

Serialize tensors using int8 views (#16866)

2025-04-19 10:28:34 -07:00

utils.py

Ensure that pid passed to kill_process_tree is int for mypy (#17051)

2025-04-23 07:32:26 -07:00