1
0
AlpinDale d69273bd2b ray: better error when placement group topology is incorrect (#906) 3 долоо хоног өмнө
..
async_aphrodite c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
basic_correctness abfd4465ca feat: add support for chunked prefill + prefix caching (#871) 1 сар өмнө
benchmarks 132aa2abe4 spec decode: add support for EAGLE (#899) 3 долоо хоног өмнө
compile c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
core abfd4465ca feat: add support for chunked prefill + prefix caching (#871) 1 сар өмнө
distributed d69273bd2b ray: better error when placement group topology is incorrect (#906) 3 долоо хоног өмнө
endpoints 6fbab320e7 api: error suppression cleanup + timeout suppression on aborts (#905) 3 долоо хоног өмнө
engine c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
kernels 93bc863591 feat: Machete Kernels for Hopper GPUs (#842) 1 сар өмнө
lora 68f050129d fix: lora worker manager test import 1 сар өмнө
metrics c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
modeling c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
models 908ff753a1 fix: phi_3.5_v loading (#896) 3 долоо хоног өмнө
multi_step 48a8693aed feat: multi-step scheduling (#831) 1 сар өмнө
multimodal c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
plugins c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
prefix_caching 3d83e64f8e feat: add metrics for prefix cache hit rate (#829) 1 сар өмнө
prompt_adapter c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
prompts e1f3fd1e02 fix: test units (#201) 1 жил өмнө
quantization 7f1c9af5e2 fix: fp8 quant test 1 сар өмнө
samplers 2150bb5019 sampler: add range parameter for DRY (#855) 1 сар өмнө
spec_decode ab533e0e60 spec decode: fix logprobs when using speculative decoding (#904) 3 долоо хоног өмнө
tensorizer_loader 32a37e8107 tests: partially fix tensorizer and logprobs tests 1 сар өмнө
tokenization c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
weight_loading c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
worker 22a4cd4595 core: fix spec decode metrics and envs circular import (#889) 3 долоо хоног өмнө
__init__.py 2755a48d51 merge dev branch into main (#153) 1 жил өмнө
conftest.py 653d1a08d4 feat: add support for audio models (#891) 3 долоо хоног өмнө
test_cache_block_hashing.py c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
test_config.py c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
test_embedded_commit.py c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
test_inputs.py c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
test_logits_processor.py c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
test_regression.py c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
test_sampling_params.py c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
test_scalartype.py c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
test_sequence.py c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
test_sharded_state_loader.py c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
test_utils.py c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө
utils.py c6c91edab7 ci: update & overhaul test units (#769) 1 сар өмнө