Oxana KorzhandClaude Opus 5 fb68025138 [Bugfix][MRV2] Release model and KV cache on in-process engine shutdown (#54162) ...

Signed-off-by: Oxana Korzh <okorzh@amd.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-08-28 22:09:08 -07:00

..

attention

[Attention][DCP] Enable FlashInfer MLA for DSpark drafting (#54277)

2026-08-28 21:11:28 -07:00

core

[Bugfix][V1] Keep an encoder cache entry until its last occurrence is freed (#54284)

2026-08-29 05:08:01 +00:00

engine

[Bugfix][MRV2] Release model and KV cache on in-process engine shutdown (#54162)

2026-08-28 22:09:08 -07:00

executor

[Bugfix] Set breakable graph env before Ray actor import (#53293)

2026-08-28 23:11:50 +00:00

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

Count store offers, not lookups, for CPU offload store_threshold (#52227)

2026-08-27 20:21:06 -07:00

metrics

[Frontend][Core][Spec Decode] Per-request acceptance stats in OpenAI API responses (#48915)

2026-08-20 15:42:49 -07:00

pool

[Pooling] Improve BGE-M3 sync pooling throughput by up to 3.13% (#53464)

2026-08-24 08:33:32 -04:00

sample

Fix seed loss when batch contains unseeded requests (#51866)

2026-08-20 22:38:53 +00:00

simple_kv_offload

[Core][KV Connector] Start async KV loads after the forward launch when no sync loads are scheduled (#53333)

2026-08-28 21:58:00 +00:00

spec_decode

[Bugfix][ROCm] Capture CUDA graphs on the current stream (#53818)

2026-08-26 23:16:45 +08:00

structured_output

[Bugfix][Structured Output] Avoid spurious FSM errors after speculative reasoning end (#53046)

2026-08-21 10:01:06 +08:00

worker

[Attention][DCP] Enable FlashInfer MLA for DSpark drafting (#54277)

2026-08-28 21:11:28 -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

[Attention][DCP] Enable FlashInfer MLA for DSpark drafting (#54277)

2026-08-28 21:11:28 -07:00

kv_cache_layout.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

kv_cache_spec_registry.py

[KVCache] Support Pluggable KVCacheSpec (#37505)

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

outputs.py

[Perf] Avoid h2d copies from non-pinned CPU tensors (#54299)

2026-08-29 12:06:30 +08:00

request.py

[Frontend][Core][Spec Decode] Per-request acceptance stats in OpenAI API responses (#48915)

2026-08-20 15:42:49 -07:00

serial_utils.py

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

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

utils.py

[Bugfix][Frontend] Keep credentials out of the Rust frontend launch log (#53738)

2026-08-25 16:32:12 +00:00