.. |
async_aphrodite
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
basic_correctness
|
abfd4465ca
feat: add support for chunked prefill + prefix caching (#871)
|
il y a 1 mois |
benchmarks
|
b5aa11020b
api: fix crashes under very high loads (#878)
|
il y a 4 semaines |
compile
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
core
|
abfd4465ca
feat: add support for chunked prefill + prefix caching (#871)
|
il y a 1 mois |
distributed
|
653d1a08d4
feat: add support for audio models (#891)
|
il y a 3 semaines |
endpoints
|
653d1a08d4
feat: add support for audio models (#891)
|
il y a 3 semaines |
engine
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
kernels
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
il y a 1 mois |
lora
|
68f050129d
fix: lora worker manager test import
|
il y a 1 mois |
metrics
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
modeling
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
models
|
653d1a08d4
feat: add support for audio models (#891)
|
il y a 3 semaines |
multi_step
|
48a8693aed
feat: multi-step scheduling (#831)
|
il y a 1 mois |
multimodal
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
plugins
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
prefix_caching
|
3d83e64f8e
feat: add metrics for prefix cache hit rate (#829)
|
il y a 1 mois |
prompt_adapter
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
prompts
|
e1f3fd1e02
fix: test units (#201)
|
il y a 1 an |
quantization
|
7f1c9af5e2
fix: fp8 quant test
|
il y a 1 mois |
samplers
|
2150bb5019
sampler: add range parameter for DRY (#855)
|
il y a 1 mois |
spec_decode
|
16b587c104
fix: hidden states handling in batch expansion for spec decoding (#839)
|
il y a 1 mois |
tensorizer_loader
|
32a37e8107
tests: partially fix tensorizer and logprobs tests
|
il y a 1 mois |
tokenization
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
weight_loading
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
worker
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
il y a 3 semaines |
__init__.py
|
2755a48d51
merge dev branch into main (#153)
|
il y a 1 an |
conftest.py
|
653d1a08d4
feat: add support for audio models (#891)
|
il y a 3 semaines |
test_cache_block_hashing.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
test_config.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
test_embedded_commit.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
test_inputs.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
test_logits_processor.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
test_regression.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
test_sampling_params.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
test_scalartype.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
test_sequence.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
test_sharded_state_loader.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
test_utils.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |
utils.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 1 mois |