Mick 24a8944e15 fix: enable Kimi multimodal breakable prefill cuda graph replay (#31391)

2026-07-17 19:13:54 +08:00

..

model_runner_components

fix: enable Kimi multimodal breakable prefill cuda graph replay (#31391)

2026-07-17 19:13:54 +08:00

test_cuda_graph_buffer_registry.py

Enable breakable prefill CUDA graph for DP attention (#30898)

2026-07-12 17:10:04 -07:00

test_forward_metadata_plan_record.py

Replace skip_attn_backend_init with a batch-carried attention plan marker (+ staleness re-plan) (#27193)

2026-06-04 17:13:18 -07:00

test_pool_configurator.py

Extract per-architecture KV-cache pool builders into KVCacheConfigurator (#31163)

2026-07-14 16:02:09 +08:00