| .. |
|
async_aphrodite
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
basic_correctness
|
2f61644f6e
SPMD optimizations (#824)
|
hai 4 meses |
|
benchmarks
|
bfc8988116
feat: add cuda sampling kernels for top_k and top_p (#828)
|
hai 4 meses |
|
compile
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
core
|
2242da5a4d
feat: add metrics for prefix cache hit rate
|
hai 4 meses |
|
distributed
|
2f61644f6e
SPMD optimizations (#824)
|
hai 4 meses |
|
endpoints
|
262cbc63b7
fix: vision api test template path
|
hai 4 meses |
|
engine
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
kernels
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
lora
|
68f050129d
fix: lora worker manager test import
|
hai 4 meses |
|
metrics
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
modeling
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
models
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
multimodal
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
plugins
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
prefix_caching
|
2242da5a4d
feat: add metrics for prefix cache hit rate
|
hai 4 meses |
|
prompt_adapter
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
prompts
|
e1f3fd1e02
fix: test units (#201)
|
hai 1 ano |
|
quantization
|
7f1c9af5e2
fix: fp8 quant test
|
hai 4 meses |
|
samplers
|
22427602eb
feat: add top-nsigma sampling method
|
hai 4 meses |
|
spec_decode
|
2f61644f6e
SPMD optimizations (#824)
|
hai 4 meses |
|
tensorizer_loader
|
32a37e8107
tests: partially fix tensorizer and logprobs tests
|
hai 4 meses |
|
tokenization
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
weight_loading
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
worker
|
2f61644f6e
SPMD optimizations (#824)
|
hai 4 meses |
|
__init__.py
|
2755a48d51
merge dev branch into main (#153)
|
hai 1 ano |
|
conftest.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
test_cache_block_hashing.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
test_config.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
test_embedded_commit.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
test_inputs.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
test_logits_processor.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
test_regression.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
test_sampling_params.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
test_scalartype.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
test_sequence.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
test_sharded_state_loader.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
test_utils.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
|
utils.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 4 meses |
AlpinDale
2242da5a4d
feat: add metrics for prefix cache hit rate