Jin HuangandJin Huang 8dd0671bac [Bugfix][V1] Only get input embeddings w/ multi-modal models if first PP (#17916) ...

Signed-off-by: Jin Huang <jinhun@amazon.com>
Co-authored-by: Jin Huang <jinhun@amazon.com>

2025-05-13 15:10:07 +08:00

..

__init__.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

block_table.py

[v1] Pass BlockTable and KVCacheSpec to AttentionMetadataBuilders (#17483)

2025-05-10 16:12:04 -07:00

gpu_input_batch.py

[v1] Pass BlockTable and KVCacheSpec to AttentionMetadataBuilders (#17483)

2025-05-10 16:12:04 -07:00

gpu_model_runner.py

[Bugfix][V1] Only get input embeddings w/ multi-modal models if first PP (#17916)

2025-05-13 15:10:07 +08:00

gpu_worker.py

[Misc] Split model loader (#17712)

2025-05-07 12:42:26 +08:00

lora_model_runner_mixin.py

Improve static type checking in LoRAModelRunnerMixin (#17104)

2025-04-24 06:14:47 -07:00

tpu_model_runner.py

[Bugfix][TPU] Use np array when updating cache slot_mapping (#17971)

2025-05-12 12:58:33 +08:00

tpu_worker.py

[Hardware][TPU][V1] Multi-LoRA implementation for the V1 TPU backend (#14238)

2025-05-07 16:28:47 -04:00

utils.py

Add full API docs and improve the UX of navigating them (#17485)

2025-05-03 19:42:43 -07:00

worker_base.py

[v1] Refactor KVCacheConfig (#14079)

2025-03-21 04:56:27 -07:00