Ma JianandKunshang Ji 8de5cabeb7 [XPU]fix: add XPU platform guards to DeepSeek-V4 ops (#42950) ...

Signed-off-by: Ma Jian <jian1.ma@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

2026-05-23 06:29:45 +08:00

..

attention

[XPU]fix: add XPU platform guards to DeepSeek-V4 ops (#42950)

2026-05-23 06:29:45 +08:00

core

[bug] AsyncScheduler drops first post-resume token after pause_generation + clear_cache (#42117)

2026-05-19 01:06:21 -07:00

engine

[Bugfix] Clear P0 mm sender cache on sleep/pause to fix mm_hash desync (#43001)

2026-05-22 03:54:29 -07:00

executor

fix nixl side-channel host selection (#41806)

2026-05-11 07:40:37 +00:00

kv_offload

[KV Offload] Pass OffloadingSpec instead of VllmConfig to secondary tiers (#43076)

2026-05-20 03:32:08 +00:00

metrics

[Bugfix][Metrics] Fix RayPrometheusMetric.labels() returning shared labeled child (#40840)

2026-05-01 08:43:39 +01:00

pool

[Misc] Replace assert with proper exceptions for security and validation in pooling (#43286)

2026-05-22 18:43:33 +08:00

sample

[BugFix] Use correct logprobs for logprob_token_ids (#43125)

2026-05-21 15:42:20 -07:00

simple_kv_offload

[Bugfix][KV Connector] Fix SimpleCPUOffloadScheduler TOCTOU between Phase A and Phase B (#42289)

2026-05-18 21:22:33 -07:00

spec_decode

[Perf] Optimize hidden state extraction logic (#37374)

2026-05-22 18:23:08 -04:00

structured_output

[Bug][Structured Outputs] Fix bug that leads to unconstrained generations with structural tags (#42452)

2026-05-20 07:08:58 -07:00

worker

[Model Runner V2] Support sharing kv cache layers (#35045)

2026-05-22 22:18:23 +00:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

cudagraph_dispatcher.py

[Experimental] Breakable CUDA graph (#42304)

2026-05-16 22:04:12 +08:00

kv_cache_interface.py

[Bugfix][Hybrid][NemotronH] Fix mamba_cache_mode=all + speculative decoding crash (#41233)

2026-05-18 14:54:00 +03:00

outputs.py

[RFC] Replace shared-memory routed experts with ModelRunnerOutput transfer and HTTP support (#39568)

2026-05-14 14:12:30 +00:00

request.py

[bug] AsyncScheduler drops first post-resume token after pause_generation + clear_cache (#42117)

2026-05-19 01:06:21 -07:00

serial_utils.py

Add tensor IPC transfer mechanism for multimodal data (#32104)

2026-03-21 20:10:20 +00:00

utils.py

[Frontend][RFC] Rust front-end integration (#40848)

2026-05-21 12:24:48 +08:00