wang.yuqi f4b76056ee

Improve enable chunked_prefill & prefix_caching logic. (#26623) ...

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

2025-11-27 22:05:48 -08:00

..

__init__.py

…

embed_utils.py

…

test_auto_prefix_cache_support.py

Improve enable chunked_prefill & prefix_caching logic. (#26623)

2025-11-27 22:05:48 -08:00

test_classification.py

VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611)

2025-11-11 18:34:36 -08:00

test_embedding.py

VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611)

2025-11-11 18:34:36 -08:00

test_extract_hidden_states.py

[Model] Allow users to control skip reading cache per request. (#28194)

2025-11-16 00:04:50 -08:00

test_gritlm.py

…

test_head_dtype.py

…

test_mm_classifier_conversion.py

[chore] Move the rest of wikimedia url to S3 (#28921)

2025-11-18 09:44:18 -08:00

test_multi_vector_retrieval.py

…

test_multilabel_classification_support.py

…

test_nomic_max_model_len.py

Update rope_scaling to rope_parameters in preparation for Transformers v5 (#28542)

2025-11-19 09:06:36 -08:00

test_pooler_config_init_behaviour.py

…

test_reward.py

VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611)

2025-11-11 18:34:36 -08:00

test_scoring.py

…

test_splade_sparse_pooler.py

…

test_token_classification.py

…

test_truncation_control.py

…