| .. |
|
async_aphrodite
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
basic_correctness
|
abfd4465ca
feat: add support for chunked prefill + prefix caching (#871)
|
hai 1 mes |
|
benchmarks
|
132aa2abe4
spec decode: add support for EAGLE (#899)
|
hai 3 semanas |
|
compile
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
core
|
abfd4465ca
feat: add support for chunked prefill + prefix caching (#871)
|
hai 1 mes |
|
distributed
|
d69273bd2b
ray: better error when placement group topology is incorrect (#906)
|
hai 3 semanas |
|
endpoints
|
6fbab320e7
api: error suppression cleanup + timeout suppression on aborts (#905)
|
hai 3 semanas |
|
engine
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
kernels
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
hai 1 mes |
|
lora
|
68f050129d
fix: lora worker manager test import
|
hai 1 mes |
|
metrics
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
modeling
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
models
|
908ff753a1
fix: phi_3.5_v loading (#896)
|
hai 3 semanas |
|
multi_step
|
48a8693aed
feat: multi-step scheduling (#831)
|
hai 1 mes |
|
multimodal
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
plugins
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
prefix_caching
|
3d83e64f8e
feat: add metrics for prefix cache hit rate (#829)
|
hai 1 mes |
|
prompt_adapter
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
prompts
|
e1f3fd1e02
fix: test units (#201)
|
hai 1 ano |
|
quantization
|
7f1c9af5e2
fix: fp8 quant test
|
hai 1 mes |
|
samplers
|
2150bb5019
sampler: add range parameter for DRY (#855)
|
hai 1 mes |
|
spec_decode
|
ab533e0e60
spec decode: fix logprobs when using speculative decoding (#904)
|
hai 3 semanas |
|
tensorizer_loader
|
673621a3d2
xpu: refactor the model runner for tensor parallelism (#910)
|
hai 3 semanas |
|
tokenization
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
weight_loading
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
worker
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
hai 3 semanas |
|
__init__.py
|
2755a48d51
merge dev branch into main (#153)
|
hai 1 ano |
|
conftest.py
|
653d1a08d4
feat: add support for audio models (#891)
|
hai 3 semanas |
|
test_cache_block_hashing.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
test_config.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
test_embedded_commit.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
test_inputs.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
test_logits_processor.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
test_regression.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
test_sampling_params.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
test_scalartype.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
test_sequence.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
test_sharded_state_loader.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
test_utils.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
|
utils.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
hai 1 mes |
AlpinDale
673621a3d2
xpu: refactor the model runner for tensor parallelism (#910)