AlpinDale 1fac86c325 core: factor out common code in SequenceData (#1083) 2 settimane fa
..
async_aphrodite 055c8905a3 api: add sampling/engine option to return only deltas or final output (#1035) 4 settimane fa
basic_correctness 7b6501bd05 tests: refactor model tests (#1078) 2 settimane fa
benchmarks 86bf2cc4f3 core: rename `PromptInputs,inputs` -> `PromptType,prompt` (#1080) 2 settimane fa
compile 239a8cae25 torch.compile: register all-reduce operations as custom ops (#1050) 3 settimane fa
core f7f3fed265 feat: add async postprocessor (#925) 1 mese fa
distributed 7b6501bd05 tests: refactor model tests (#1078) 2 settimane fa
encoder_decoder a985143768 core: add cuda graph support for encoder-decoder models (#1051) 3 settimane fa
endpoints 6212072245 api: support LoRA lineage and base model metadata management (#1072) 3 settimane fa
engine 3bb0f07461 chore: rename `task_handler` to `worker` (#985) 1 mese fa
kernels 7b6501bd05 tests: refactor model tests (#1078) 2 settimane fa
lora 3bb0f07461 chore: rename `task_handler` to `worker` (#985) 1 mese fa
metrics c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
modeling c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
models 86bf2cc4f3 core: rename `PromptInputs,inputs` -> `PromptType,prompt` (#1080) 2 settimane fa
mq_aphrodite_engine 86bf2cc4f3 core: rename `PromptInputs,inputs` -> `PromptType,prompt` (#1080) 2 settimane fa
multi_step 58aff3771d core: support prompt logprobs in multi-step (#1060) 3 settimane fa
multimodal 2aabf8fcf7 vlm: fix errors on ragged NestedTensors (#953) 1 mese fa
plugins c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
prefix_caching 6212072245 api: support LoRA lineage and base model metadata management (#1072) 3 settimane fa
prompt_adapter c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
prompts e1f3fd1e02 fix: test units (#201) 1 anno fa
quantization 6bdff60aab quant: support pre-quanted bitsandbytes checkpoints (#961) 1 mese fa
samplers 1fac86c325 core: factor out common code in SequenceData (#1083) 2 settimane fa
spec_decode 1fac86c325 core: factor out common code in SequenceData (#1083) 2 settimane fa
tensorizer_loader 673621a3d2 xpu: refactor the model runner for tensor parallelism (#910) 1 mese fa
tokenization c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
tool_use 0191c5efd1 tools: fix tool calls to more strictly follow OpenAI format (#1003) 4 settimane fa
tpu ea59784f59 tpu: remove torch._dynamo.reset() (#952) 1 mese fa
weight_loading c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
worker 1fac86c325 core: factor out common code in SequenceData (#1083) 2 settimane fa
__init__.py 2755a48d51 merge dev branch into main (#153) 1 anno fa
conftest.py 7b6501bd05 tests: refactor model tests (#1078) 2 settimane fa
test_cache_block_hashing.py c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
test_config.py c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
test_embedded_commit.py c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
test_inputs.py c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
test_logits_processor.py 1fac86c325 core: factor out common code in SequenceData (#1083) 2 settimane fa
test_regression.py c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
test_sampling_params.py c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
test_scalartype.py c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
test_sequence.py 1fac86c325 core: factor out common code in SequenceData (#1083) 2 settimane fa
test_sharded_state_loader.py c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
test_utils.py c6c91edab7 ci: update & overhaul test units (#769) 2 mesi fa
utils.py 7b6501bd05 tests: refactor model tests (#1078) 2 settimane fa