Kebe 51dd14ac2b

[Bugfix][DP] Fix creating too many DP Placement Groups (#26880) ...

Signed-off-by: Kebe <mail@kebe7jun.com>
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
Co-authored-by: Rui Qiao <ruisearch42@gmail.com>

2025-10-23 20:16:51 +00:00

..

attention

[Attention] Fix FlashMLA metadata builder arguments for q_len > 1 (#27368)

2025-10-23 15:58:15 -04:00

core

[Metrics] [KVConnector] Add connector prefix cache hit rate stats (#26245)

2025-10-23 12:21:08 +02:00

engine

[Bugfix][DP] Fix creating too many DP Placement Groups (#26880)

2025-10-23 20:16:51 +00:00

executor

[Chore] Separate out system utilities from vllm.utils (#27201)

2025-10-22 20:25:25 +00:00

kv_offload

[Chore] Separate out vllm.utils.platform_utils.py (#27374)

2025-10-23 19:08:06 +00:00

metrics

[Metrics] [KVConnector] Add connector prefix cache hit rate stats (#26245)

2025-10-23 12:21:08 +02:00

pool

[Chore] Separate out vllm.utils.platform_utils.py (#27374)

2025-10-23 19:08:06 +00:00

sample

[Chore] Separate out vllm.utils.platform_utils.py (#27374)

2025-10-23 19:08:06 +00:00

spec_decode

[Chore] Separate out vllm.utils.platform_utils.py (#27374)

2025-10-23 19:08:06 +00:00

structured_output

Updated xgrammar backend to not deny supported string formats (#27253)

2025-10-21 22:25:23 +00:00

worker

[Chore] Separate out vllm.utils.platform_utils.py (#27374)

2025-10-23 19:08:06 +00:00

__init__.py

…

cudagraph_dispatcher.py

[LoRA] LoRA cuda graph specialization (#25914)

2025-10-20 04:21:09 +00:00

kv_cache_interface.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

2025-10-18 09:48:22 -07:00

outputs.py

[V1][spec decode] return logprobs for spec decoding (#26060)

2025-10-22 22:59:59 -07:00

request.py

[Core] Streamline some structured output related code (#26737)

2025-10-14 23:27:44 +00:00

serial_utils.py

[CORE] Support Prefix Caching with Prompt Embeds (#27219)

2025-10-22 22:18:07 -07:00

utils.py

[CORE] Support Prefix Caching with Prompt Embeds (#27219)

2025-10-22 22:18:07 -07:00