| .. |
|
__init__.py
|
04b53d2db5
chore: add initializer files
|
1 年間 前 |
|
cache_engine.py
|
bf88c8567e
feat: mamba model support (#674)
|
4 ヶ月 前 |
|
cpu_model_runner.py
|
55b7ce56c1
cpu: fix `mm_limits` initialization (#873)
|
1 ヶ月 前 |
|
cpu_worker.py
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 ヶ月 前 |
|
embedding_model_runner.py
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 ヶ月 前 |
|
enc_dec_model_runner.py
|
1405051912
attention: add `AttentionState` abstraction (#863)
|
1 ヶ月 前 |
|
model_runner.py
|
abfd4465ca
feat: add support for chunked prefill + prefix caching (#871)
|
1 ヶ月 前 |
|
model_runner_base.py
|
48a8693aed
feat: multi-step scheduling (#831)
|
1 ヶ月 前 |
|
multi_step_model_runner.py
|
48a8693aed
feat: multi-step scheduling (#831)
|
1 ヶ月 前 |
|
multi_step_worker.py
|
48a8693aed
feat: multi-step scheduling (#831)
|
1 ヶ月 前 |
|
neuron_model_runner.py
|
008e646c7e
chore: add support for up to 2048 block size (#715)
|
3 ヶ月 前 |
|
neuron_worker.py
|
008e646c7e
chore: add support for up to 2048 block size (#715)
|
3 ヶ月 前 |
|
openvino_model_runner.py
|
bf88c8567e
feat: mamba model support (#674)
|
4 ヶ月 前 |
|
openvino_worker.py
|
bf88c8567e
feat: mamba model support (#674)
|
4 ヶ月 前 |
|
tpu_model_runner.py
|
81c5f196eb
chore: various TPU fixes and optimizations (#746)
|
3 ヶ月 前 |
|
tpu_worker.py
|
81c5f196eb
chore: various TPU fixes and optimizations (#746)
|
3 ヶ月 前 |
|
utils.py
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 ヶ月 前 |
|
worker.py
|
48a8693aed
feat: multi-step scheduling (#831)
|
1 ヶ月 前 |
|
worker_base.py
|
48a8693aed
feat: multi-step scheduling (#831)
|
1 ヶ月 前 |
|
xpu_model_runner.py
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 ヶ月 前 |
|
xpu_worker.py
|
9094a8a2a3
xpu: refactor XPU worker & executor (#861)
|
1 ヶ月 前 |
AlpinDale
55b7ce56c1
cpu: fix `mm_limits` initialization (#873)