Roger Wang 755492e37d Revert "[Kernel] Gemma-4 FA4 FP8 Kernel" (#52987)

2026-08-19 10:48:46 -07:00

..

attention

Revert "[Kernel] Gemma-4 FA4 FP8 Kernel" (#52987)

2026-08-19 10:48:46 -07:00

core

[Core] Skip broadcasting mm tensor data to workers for prefix-cache-covered items (#52041)

2026-08-19 07:16:39 -07:00

engine

[Bugfix][V1] Sync mamba_block_size via EngineCoreReadyResponse (#50809)

2026-08-19 16:44:36 +00:00

executor

[Bugfix] Account for local DP workers in startup thread allocation (#52385)

2026-08-17 12:10:34 -07:00

fault_tolerance

[Feature] Add fault tolerance framework (simplified) for DP+EP external LB deployments (#44428)

2026-07-25 11:49:09 -04:00

kv_offload

[Core] Make prefix-cache NONE_HASH deterministic by default (#51875)

2026-08-18 23:14:39 +00:00

metrics

[Migration] Migrate bitsandbytes support to OOT plugin (#43529)

2026-08-09 10:27:31 +08:00

pool

[Core] Move MRV1 late_interaction_runner.py out of MRV2 subtree (#48014)

2026-07-08 18:30:11 +00:00

sample

[Platform] Fill in the missing backend parameter for torch.compile (#51781)

2026-08-19 10:31:19 +00:00

simple_kv_offload

Promote prefix_cache_retention_interval to an argument and change the default to 0 (#52216)

2026-08-17 13:20:50 +00:00

spec_decode

[Model][NVIDIA] Route DSA models to the CUDA non-compiled path (#52861)

2026-08-19 00:13:52 -07:00

structured_output

fix: reject string schemas that mix pattern/format with length bounds (#49996)

2026-08-19 17:29:32 +08:00

worker

Revert "[Kernel] Gemma-4 FA4 FP8 Kernel" (#52987)

2026-08-19 10:48:46 -07:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

cudagraph_dispatcher.py

[Model] Add DiffusionGemma Support (#45163)

2026-06-11 22:17:35 -07:00

kv_cache_interface.py

Promote prefix_cache_retention_interval to an argument and change the default to 0 (#52216)

2026-08-17 13:20:50 +00:00

kv_cache_spec_registry.py

[KVCache] Support Pluggable KVCacheSpec (#37505)

2026-06-03 09:05:16 -07:00

outputs.py

[EC Connector] Added Build Connector Worker Meta for EC Connector (#49585)

2026-08-15 15:40:38 -07:00

request.py

[ModelRunnerV2] Support prompt embeds (#42963)

2026-08-17 21:58:50 +00:00

serial_utils.py

[Core] Ensure memory is pinned prior to async h2d copy (#45424)

2026-06-20 20:02:24 -07:00

utils.py

[Frontend] Move api_server.py out openai folder (#52131)

2026-08-19 09:43:46 +00:00