AlpinDale eb1ffacf74 Spec Decoding: fix typical acceptance sampler with correct recovered tok IDs (#1106) 1 viikko sitten
..
async_aphrodite 055c8905a3 api: add sampling/engine option to return only deltas or final output (#1035) 1 kuukausi sitten
basic_correctness 7b6501bd05 tests: refactor model tests (#1078) 4 viikkoa sitten
benchmarks 86bf2cc4f3 core: rename `PromptInputs,inputs` -> `PromptType,prompt` (#1080) 3 viikkoa sitten
compile 239a8cae25 torch.compile: register all-reduce operations as custom ops (#1050) 1 kuukausi sitten
core f7f3fed265 feat: add async postprocessor (#925) 1 kuukausi sitten
distributed c90abcc603 VLM: add pipeline parallelism support for Qwen2-VL (#1103) 1 viikko sitten
encoder_decoder a985143768 core: add cuda graph support for encoder-decoder models (#1051) 1 kuukausi sitten
endpoints 6212072245 api: support LoRA lineage and base model metadata management (#1072) 1 kuukausi sitten
engine cc5e185795 VLM: support passing multimodal processor kwargs (#1102) 1 viikko sitten
kernels 7b6501bd05 tests: refactor model tests (#1078) 4 viikkoa sitten
lora 69cf654901 LoRA: add assertions for SGMV kernels to avoid incorrect results (#1104) 1 viikko sitten
metrics c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
modeling c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
models cc5e185795 VLM: support passing multimodal processor kwargs (#1102) 1 viikko sitten
mq_aphrodite_engine 86bf2cc4f3 core: rename `PromptInputs,inputs` -> `PromptType,prompt` (#1080) 3 viikkoa sitten
multi_step 58aff3771d core: support prompt logprobs in multi-step (#1060) 1 kuukausi sitten
multimodal cc5e185795 VLM: support passing multimodal processor kwargs (#1102) 1 viikko sitten
plugins c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
prefix_caching 6212072245 api: support LoRA lineage and base model metadata management (#1072) 1 kuukausi sitten
prompt_adapter c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
prompts e1f3fd1e02 fix: test units (#201) 1 vuosi sitten
quantization 6bdff60aab quant: support pre-quanted bitsandbytes checkpoints (#961) 1 kuukausi sitten
samplers eb1ffacf74 Spec Decoding: fix typical acceptance sampler with correct recovered tok IDs (#1106) 1 viikko sitten
spec_decode 1fac86c325 core: factor out common code in SequenceData (#1083) 3 viikkoa sitten
tensorizer_loader 673621a3d2 xpu: refactor the model runner for tensor parallelism (#910) 1 kuukausi sitten
tokenization c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
tool_use 0191c5efd1 tools: fix tool calls to more strictly follow OpenAI format (#1003) 1 kuukausi sitten
tpu ea59784f59 tpu: remove torch._dynamo.reset() (#952) 1 kuukausi sitten
weight_loading c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
worker 1fac86c325 core: factor out common code in SequenceData (#1083) 3 viikkoa sitten
__init__.py 2755a48d51 merge dev branch into main (#153) 1 vuosi sitten
conftest.py 7b6501bd05 tests: refactor model tests (#1078) 4 viikkoa sitten
test_cache_block_hashing.py c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
test_config.py c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
test_embedded_commit.py c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
test_inputs.py c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
test_logits_processor.py 1fac86c325 core: factor out common code in SequenceData (#1083) 3 viikkoa sitten
test_regression.py c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
test_sampling_params.py c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
test_scalartype.py c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
test_sequence.py 1fac86c325 core: factor out common code in SequenceData (#1083) 3 viikkoa sitten
test_sharded_state_loader.py c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
test_utils.py c6c91edab7 ci: update & overhaul test units (#769) 2 kuukautta sitten
utils.py 7b6501bd05 tests: refactor model tests (#1078) 4 viikkoa sitten