| .. |
|
__init__.py
|
Change the name to vLLM (#150)
|
2023-06-17 03:07:40 -07:00 |
|
cache_engine.py
|
[Kernel] Support sliding window in flash attention backend (#9403)
|
2024-10-20 10:57:52 -07:00 |
|
cpu_embedding_model_runner.py
|
[Bugfix][CPU] Fix CPU embedding runner with tensor parallel (#10394)
|
2024-11-16 23:12:04 -08:00 |
|
cpu_enc_dec_model_runner.py
|
[Bugfix][Hardware][CPU] Fix broken encoder-decoder CPU runner (#10218)
|
2024-11-11 12:37:58 +00:00 |
|
cpu_model_runner.py
|
[Hardware][CPU] Support chunked-prefill and prefix-caching on CPU (#10355)
|
2024-11-20 10:57:39 +00:00 |
|
cpu_worker.py
|
[Hardware][CPU] Add embedding models support for CPU backend (#10193)
|
2024-11-11 08:54:28 +00:00 |
|
embedding_model_runner.py
|
[0/N] Rename MultiModalInputs to MultiModalKwargs (#10040)
|
2024-11-09 11:31:02 +08:00 |
|
enc_dec_model_runner.py
|
[Platform][Refactor] Extract func get_default_attn_backend to Platform (#10358)
|
2024-11-19 11:22:26 +08:00 |
|
hpu_model_runner.py
|
[Hardware] [HPU]add mark_step for hpu (#10239)
|
2024-11-17 00:44:44 -08:00 |
|
hpu_worker.py
|
[Hardware][Intel-Gaudi] Add Intel Gaudi (HPU) inference backend (#6143)
|
2024-11-06 01:09:10 -08:00 |
|
model_runner_base.py
|
[2/N] executor pass the complete config to worker/modelrunner (#9938)
|
2024-11-02 07:35:05 -07:00 |
|
model_runner.py
|
[5/N][torch.compile] torch.jit.script --> torch.compile (#10406)
|
2024-11-18 23:20:06 +08:00 |
|
multi_step_model_runner.py
|
[2/N] executor pass the complete config to worker/modelrunner (#9938)
|
2024-11-02 07:35:05 -07:00 |
|
multi_step_tpu_worker.py
|
[TPU] Implement multi-step scheduling (#8489)
|
2024-09-14 16:58:31 -07:00 |
|
multi_step_worker.py
|
[2/N] executor pass the complete config to worker/modelrunner (#9938)
|
2024-11-02 07:35:05 -07:00 |
|
neuron_model_runner.py
|
[1/N] Initial prototype for multi-modal processor (#10044)
|
2024-11-13 12:39:03 +00:00 |
|
neuron_worker.py
|
[2/N] executor pass the complete config to worker/modelrunner (#9938)
|
2024-11-02 07:35:05 -07:00 |
|
openvino_model_runner.py
|
[1/N] Initial prototype for multi-modal processor (#10044)
|
2024-11-13 12:39:03 +00:00 |
|
openvino_worker.py
|
[2/N] executor pass the complete config to worker/modelrunner (#9938)
|
2024-11-02 07:35:05 -07:00 |
|
tpu_model_runner.py
|
[TPU] Implement prefix caching for TPUs (#10307)
|
2024-11-20 13:54:15 -08:00 |
|
tpu_worker.py
|
[TPU] Implement prefix caching for TPUs (#10307)
|
2024-11-20 13:54:15 -08:00 |
|
utils.py
|
[Doc] Compatibility matrix for mutual exclusive features (#8512)
|
2024-10-11 11:18:50 -07:00 |
|
worker_base.py
|
[2/N] executor pass the complete config to worker/modelrunner (#9938)
|
2024-11-02 07:35:05 -07:00 |
|
worker.py
|
[7/N] torch.compile, reduce compilation time (#10460)
|
2024-11-20 11:20:38 -08:00 |
|
xpu_model_runner.py
|
[1/N] Initial prototype for multi-modal processor (#10044)
|
2024-11-13 12:39:03 +00:00 |
|
xpu_worker.py
|
[2/N] executor pass the complete config to worker/modelrunner (#9938)
|
2024-11-02 07:35:05 -07:00 |
