AlpinDale c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) 1 rok temu
..
__init__.py 07aa2a492f upstream: add option to specify tokenizer 1 rok temu
block.py 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 rok temu
config.py c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) 1 rok temu
grammar.py 0adab894fe feat: grammar support (#206) 1 rok temu
logger.py 8834ecf9de chore: clean up refactor endpoints (#98) 1 rok temu
logits_processor.py 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 rok temu
outputs.py c0aac15421 feat: S-LoRA support (#222) 1 rok temu
prefix.py c0aac15421 feat: S-LoRA support (#222) 1 rok temu
sampling_params.py 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 rok temu
sequence.py c0aac15421 feat: S-LoRA support (#222) 1 rok temu
test_utils.py 641bb0f6e9 feat: add custom allreduce kernels (#224) 1 rok temu
utils.py 31c95011a6 feat: FP8 E5M2 KV Cache (#226) 1 rok temu