| .. |
|
async_aphrodite
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
basic_correctness
|
f7f3fed265
feat: add async postprocessor (#925)
|
1 месяц назад |
|
benchmarks
|
f7f3fed265
feat: add async postprocessor (#925)
|
1 месяц назад |
|
compile
|
0e5cf7f840
tpu: avoid dynamo guard eval overhead (#949)
|
1 месяц назад |
|
core
|
f7f3fed265
feat: add async postprocessor (#925)
|
1 месяц назад |
|
distributed
|
a8bdd488b9
distributed: support pipeline parallelism for internvl and internlm2 (#965)
|
1 месяц назад |
|
endpoints
|
0f72141ca2
api: support multiple input images
|
1 месяц назад |
|
engine
|
f7f3fed265
feat: add async postprocessor (#925)
|
1 месяц назад |
|
kernels
|
a90d41d908
tests: add kernel tests for causal_conv1d and mamba_ssm (#947)
|
1 месяц назад |
|
lora
|
68f050129d
fix: lora worker manager test import
|
2 месяцев назад |
|
metrics
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
modeling
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
models
|
7eeee771f2
tests: update internvl test for #971 (#972)
|
1 месяц назад |
|
multi_step
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
1 месяц назад |
|
multimodal
|
2aabf8fcf7
vlm: fix errors on ragged NestedTensors (#953)
|
1 месяц назад |
|
plugins
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
prefix_caching
|
3d83e64f8e
feat: add metrics for prefix cache hit rate (#829)
|
2 месяцев назад |
|
prompt_adapter
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
prompts
|
e1f3fd1e02
fix: test units (#201)
|
1 год назад |
|
quantization
|
6bdff60aab
quant: support pre-quanted bitsandbytes checkpoints (#961)
|
1 месяц назад |
|
samplers
|
2150bb5019
sampler: add range parameter for DRY (#855)
|
1 месяц назад |
|
spec_decode
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
1 месяц назад |
|
tensorizer_loader
|
673621a3d2
xpu: refactor the model runner for tensor parallelism (#910)
|
1 месяц назад |
|
tokenization
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
tpu
|
ea59784f59
tpu: remove torch._dynamo.reset() (#952)
|
1 месяц назад |
|
weight_loading
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
worker
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
1 месяц назад |
|
__init__.py
|
2755a48d51
merge dev branch into main (#153)
|
1 год назад |
|
conftest.py
|
6bdff60aab
quant: support pre-quanted bitsandbytes checkpoints (#961)
|
1 месяц назад |
|
test_cache_block_hashing.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
test_config.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
test_embedded_commit.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
test_inputs.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
test_logits_processor.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
test_regression.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
test_sampling_params.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
test_scalartype.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
test_sequence.py
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
1 месяц назад |
|
test_sharded_state_loader.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
test_utils.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
2 месяцев назад |
|
utils.py
|
a8bdd488b9
distributed: support pipeline parallelism for internvl and internlm2 (#965)
|
1 месяц назад |
AlpinDale
0f72141ca2
api: support multiple input images