Chengji Yao 0578e5a462 [Hardware][TPU]Enable ragged paged attention kernel and resolve recompilation issue (#14310) ...

Signed-off-by: Chengji Yao <chengjiyao@google.com>

2025-03-06 23:31:05 +00:00

..

__init__.py

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

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

block_table.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

gpu_input_batch.py

[BugFix] MLA + V1, illegal memory access and accuracy issues (#14253)

2025-03-05 17:10:13 -08:00

gpu_model_runner.py

[BugFix] MLA + V1, illegal memory access and accuracy issues (#14253)

2025-03-05 17:10:13 -08:00

gpu_worker.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

lora_model_runner_mixin.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

tpu_model_runner.py

[Hardware][TPU]Enable ragged paged attention kernel and resolve recompilation issue (#14310)

2025-03-06 23:31:05 +00:00

tpu_worker.py

[V1][TPU] TPU multimodal model support for ragged attention (#14158)

2025-03-04 19:58:48 -05:00

worker_base.py

[v1] fix parallel config rank (#13445)

2025-02-18 12:33:45 +08:00