AlpinDale 2d7929d3b7 fix: flashinfer crash with uneven attention group_size 1 ヶ月 前
..
async_aphrodite c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
basic_correctness abfd4465ca feat: add support for chunked prefill + prefix caching (#871) 1 ヶ月 前
benchmarks 93bc863591 feat: Machete Kernels for Hopper GPUs (#842) 1 ヶ月 前
compile c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
core abfd4465ca feat: add support for chunked prefill + prefix caching (#871) 1 ヶ月 前
distributed 2f61644f6e SPMD optimizations (#824) 1 ヶ月 前
endpoints 262cbc63b7 fix: vision api test template path 1 ヶ月 前
engine c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
kernels 2d7929d3b7 fix: flashinfer crash with uneven attention group_size 1 ヶ月 前
lora 68f050129d fix: lora worker manager test import 1 ヶ月 前
metrics c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
modeling c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
models e182d00256 feat: AWQ quantization for InternVL (#867) 1 ヶ月 前
multi_step 48a8693aed feat: multi-step scheduling (#831) 1 ヶ月 前
multimodal c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
plugins c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
prefix_caching 3d83e64f8e feat: add metrics for prefix cache hit rate (#829) 1 ヶ月 前
prompt_adapter c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
prompts e1f3fd1e02 fix: test units (#201) 1 年間 前
quantization 7f1c9af5e2 fix: fp8 quant test 1 ヶ月 前
samplers 2150bb5019 sampler: add range parameter for DRY (#855) 1 ヶ月 前
spec_decode 16b587c104 fix: hidden states handling in batch expansion for spec decoding (#839) 1 ヶ月 前
tensorizer_loader 32a37e8107 tests: partially fix tensorizer and logprobs tests 1 ヶ月 前
tokenization c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
weight_loading c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
worker 48a8693aed feat: multi-step scheduling (#831) 1 ヶ月 前
__init__.py 2755a48d51 merge dev branch into main (#153) 1 年間 前
conftest.py c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
test_cache_block_hashing.py c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
test_config.py c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
test_embedded_commit.py c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
test_inputs.py c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
test_logits_processor.py c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
test_regression.py c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
test_sampling_params.py c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
test_scalartype.py c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
test_sequence.py c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
test_sharded_state_loader.py c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
test_utils.py c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前
utils.py c6c91edab7 ci: update & overhaul test units (#769) 1 ヶ月 前