| .. |
|
async_aphrodite
|
055c8905a3
api: add sampling/engine option to return only deltas or final output (#1035)
|
1 week ago |
|
basic_correctness
|
304e1e5a8a
core: dump model runner inputs during crash (#1023)
|
1 week ago |
|
benchmarks
|
b47a39026d
feat: introduce MQAphroditeEngine
|
1 week ago |
|
compile
|
239a8cae25
torch.compile: register all-reduce operations as custom ops (#1050)
|
1 week ago |
|
core
|
f7f3fed265
feat: add async postprocessor (#925)
|
2 weeks ago |
|
distributed
|
4d14bd1fe5
vlm: add multi-input support for LLaVA and InternVL models (#1002)
|
2 weeks ago |
|
encoder_decoder
|
a985143768
core: add cuda graph support for encoder-decoder models (#1051)
|
1 week ago |
|
endpoints
|
f644e10449
vlm: enable multimodal inputs for the LLM class (#992)
|
2 weeks ago |
|
engine
|
3bb0f07461
chore: rename `task_handler` to `worker` (#985)
|
2 weeks ago |
|
kernels
|
9bdf8d5bfa
mamba: enable continuous batching for mamba kernels (#1055)
|
1 week ago |
|
lora
|
3bb0f07461
chore: rename `task_handler` to `worker` (#985)
|
2 weeks ago |
|
metrics
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
modeling
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
models
|
8d5d87e687
vlm: support multiple images for qwen-vl (#1031)
|
1 week ago |
|
multi_step
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 weeks ago |
|
multimodal
|
2aabf8fcf7
vlm: fix errors on ragged NestedTensors (#953)
|
2 weeks ago |
|
plugins
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
prefix_caching
|
3d83e64f8e
feat: add metrics for prefix cache hit rate (#829)
|
1 month ago |
|
prompt_adapter
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
prompts
|
e1f3fd1e02
fix: test units (#201)
|
1 year ago |
|
quantization
|
6bdff60aab
quant: support pre-quanted bitsandbytes checkpoints (#961)
|
2 weeks ago |
|
samplers
|
2150bb5019
sampler: add range parameter for DRY (#855)
|
1 month ago |
|
spec_decode
|
0859dc3bc0
tests: refactor speculative decoding tests to remove the async engine (#1021)
|
1 week ago |
|
tensorizer_loader
|
673621a3d2
xpu: refactor the model runner for tensor parallelism (#910)
|
3 weeks ago |
|
tokenization
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
tool_use
|
0191c5efd1
tools: fix tool calls to more strictly follow OpenAI format (#1003)
|
2 weeks ago |
|
tpu
|
ea59784f59
tpu: remove torch._dynamo.reset() (#952)
|
2 weeks ago |
|
weight_loading
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
worker
|
a985143768
core: add cuda graph support for encoder-decoder models (#1051)
|
1 week ago |
|
__init__.py
|
2755a48d51
merge dev branch into main (#153)
|
1 year ago |
|
conftest.py
|
1721bea53a
vlm: add support for Pixtral model (#1022)
|
1 week ago |
|
test_cache_block_hashing.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
test_config.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
test_embedded_commit.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
test_inputs.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
test_logits_processor.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
test_regression.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
test_sampling_params.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
test_scalartype.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
test_sequence.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
2 weeks ago |
|
test_sharded_state_loader.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
test_utils.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 month ago |
|
utils.py
|
18acf7eaa0
tests: map physical device indices for test utils
|
1 week ago |
AlpinDale
b47a39026d
feat: introduce MQAphroditeEngine