AlpinDale 3f712cd287 feat: add progress bar for loading individual weight modules (#640) hai 6 meses
..
adapter_commons f1d0b77c92 [0.6.0] Release Candidate (#481) hai 6 meses
attention 300f889554 chore: update flashinfer to v0.1.3 (#685) hai 6 meses
common 3f712cd287 feat: add progress bar for loading individual weight modules (#640) hai 6 meses
distributed 31f82da8bd chore: deduplicate nvlink check to cuda platform (#643) hai 6 meses
endpoints 81fa31bcaf feat: embeddings support for batched OAI endpoint (#676) hai 6 meses
engine bf88c8567e feat: mamba model support (#674) hai 6 meses
executor f1d0b77c92 [0.6.0] Release Candidate (#481) hai 6 meses
inputs 62111fab17 feat: allow serving encoder-decoder models in the API server (#664) hai 6 meses
kv_quant e42a78381a feat: switch from pylint to ruff (#322) hai 1 ano
lora 1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671) hai 6 meses
modeling 3f712cd287 feat: add progress bar for loading individual weight modules (#640) hai 6 meses
multimodal 2573b36f6a feat: allow image embeddings for VLM input (#686) hai 6 meses
platforms 31f82da8bd chore: deduplicate nvlink check to cuda platform (#643) hai 6 meses
processing 79d603954e fix: chunked prefill with v2 block manager (#679) hai 6 meses
prompt_adapter f1d0b77c92 [0.6.0] Release Candidate (#481) hai 6 meses
quantization 3f49a55f82 feat: add INT8 W8A16 quant for TPU (#663) hai 6 meses
server ed9a6f97c1 fix: kill api server when pinging dead engine (#660) hai 6 meses
spec_decode 1394008421 chore: decouple `should_modify_greedy_probs_inplace (#671) hai 6 meses
task_handler b03fa02397 refactor: base worker input refactor for multi-step (#683) hai 6 meses
transformers_utils 3648170750 fix: gracefully handle missing chat template (#642) hai 6 meses
triton_utils f1d0b77c92 [0.6.0] Release Candidate (#481) hai 6 meses
__init__.py f1d0b77c92 [0.6.0] Release Candidate (#481) hai 6 meses
_core_ext.py f1d0b77c92 [0.6.0] Release Candidate (#481) hai 6 meses
_custom_ops.py a401f8e05d feat: per-tensor token epilogue kernels (#630) hai 6 meses
_ipex_ops.py f1d0b77c92 [0.6.0] Release Candidate (#481) hai 6 meses
py.typed 1c988a48b2 fix logging and add py.typed hai 1 ano
scalar_type.py f1d0b77c92 [0.6.0] Release Candidate (#481) hai 6 meses
version.py db81a67c54 bump to v0.6.0.post1 (#635) hai 6 meses