3 people 33212db2c2 [KV Connector][NIXL] Reject NVFP4 KV cache with heterogeneous TP head split (#61865) ...

Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>

2026-10-15 13:57:37 -07:00

..

aux_output_connector

[Bugfix][DSv4.1] Skip SWA bounded replay for KV loads that carry the window (#59197)

2026-10-07 15:28:42 -07:00

device_communicators

[Core] Remove the legacy Ray compiled-graph executor (#61712)

2026-10-14 18:13:27 -07:00

ec_transfer

[Bugfix][EC Connector] Don't create hash directories on cache-miss lookups in ECExampleConnector (#60826)

2026-10-13 15:59:48 +08:00

elastic_ep

[ModelRunner V2] Speculative Decoding NGram GPU Implementations (#40704)

2026-10-06 13:32:59 -07:00

eplb

[MRV2] Keep warmup out of the EPLB load stats (#56716)

2026-10-14 00:00:48 +00:00

kv_transfer

[KV Connector][NIXL] Reject NVFP4 KV cache with heterogeneous TP head split (#61865)

2026-10-15 13:57:37 -07:00

weight_transfer

[Core] Remove the legacy Ray compiled-graph executor (#61712)

2026-10-14 18:13:27 -07:00

__init__.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

communication_op.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

kv_events.py

[Core][BugFix] Tag prefix-cache extra keys by source (#51899)

2026-09-29 18:24:59 -07:00

mooncake_store.py

[Feature][Multimodal] Add cross-encoder caching to Mooncake P2P (#56242)

2026-09-17 13:16:41 +08:00

nixl_utils.py

[NIXL] Prepare KV transfer descriptors as NIXL 1.5 strided lists (#61032)

2026-10-14 18:07:24 +02:00

parallel_state.py

[sharded state loader] support pp in sharded state loader (#52110)

2026-10-09 11:08:31 -07:00

stateless_coordinator.py

[Bugfix][FT] Pass stateless process-group timeouts explicitly (#58611)

2026-09-29 03:14:02 +00:00

utils.py

Remove Python 3.10 support now that it is EOL (#60402)

2026-10-08 02:30:52 -07:00