Benjamin ChislettandNicolò Lucchesi 7fb9c0197a [Bugfix][DFlash]allocate the proper number of lookahead slots (#43733) ...

Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>

2026-05-27 21:45:34 +00:00

..

attention

[MLA][Attention] Add OOT MLA prefill backend registration mechanism (#43325)

2026-05-26 19:56:09 -07:00

core

[Bugfix][DFlash]allocate the proper number of lookahead slots (#43733)

2026-05-27 21:45:34 +00:00

engine

[KVConnector][Mooncake] Wire reset_cache cascade end-to-end (#42694)

2026-05-26 20:52:35 -07:00

executor

fix nixl side-channel host selection (#41806)

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

kv_offload

File system secondary tier implemented in python (#41735)

2026-05-24 18:14:44 +00:00

metrics

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

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

pool

[Misc] Added missing return type annotations to improve mypy and IDE tooling (#43383)

2026-05-23 13:28:22 +08:00

sample

[XPU] Ensure RNG offset alignment with PyTorch requirements in XPU sampler (#43028)

2026-05-26 02:01:30 +00:00

simple_kv_offload

[Feat][KVConnector] Support DSV4 in SimpleCPUOffloadBackend (#42296)

2026-05-25 14:04:30 +08:00

spec_decode

[ROCm] [DSv4] [Perf] Support DeepSeek v4 MTP (#43385)

2026-05-24 18:43:08 +08:00

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

[MRV2][BugFix] Fix KV connector handling in spec decode case (#43719)

2026-05-27 06:37:56 +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

[Bugfix][V1] Fix TOCTOU race causing intermittent EADDRINUSE on multi-API-server DP startup (#42585)

2026-05-26 14:06:00 -07:00