Ekagra RanjanandNicolò Lucchesi cd81cdb399 [Scheduler][ASR] Fix CrossAttn blocks per-request for Variable length encoder inputs (#31058) ...

Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>

2026-02-16 11:08:44 +00:00

..

__init__.py

…

test_async_scheduler.py

[Bugfix][Core] Fix CPU memory leak from Request reference cycle in prefix caching (#34183)

2026-02-10 13:03:32 +08:00

test_encoder_cache_manager.py

[Misc] Make PlaceholderRange.get_num_embeds a method (#34035)

2026-02-07 05:30:17 +00:00

test_kv_cache_metrics.py

…

test_kv_cache_utils.py

[Refactor] Simplify BOS/EOS token handling (#34435)

2026-02-12 18:18:24 -08:00

test_kv_sharing.py

…

test_output.py

…

test_prefix_caching.py

[Bug Fix] Fix MambaManager.cache_blocks() crash on null blocks in align mode (#34418)

2026-02-13 00:13:22 -08:00

test_priority_scheduler_random.py

[Refactor] Simplify BOS/EOS token handling (#34435)

2026-02-12 18:18:24 -08:00

test_reset_prefix_cache_e2e.py

…

test_scheduler_e2e.py

…

test_scheduler.py

[Scheduler][ASR] Fix CrossAttn blocks per-request for Variable length encoder inputs (#31058)

2026-02-16 11:08:44 +00:00

test_single_type_kv_cache_manager.py

…

utils.py

[Refactor] Simplify BOS/EOS token handling (#34435)

2026-02-12 18:18:24 -08:00