50h100a f663d3fccc Merge pull request #397 from 50h100a/pr_samplerasserts 11 mesi fa
..
layers f663d3fccc Merge pull request #397 from 50h100a/pr_samplerasserts 11 mesi fa
megatron 29c241c115 fix: explicitly disallow installation on non-linux platforms (#373) 11 mesi fa
models 72cd8494aa feat: mistral neuron support (#368) 11 mesi fa
__init__.py 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 anno fa
hf_downloader.py f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 11 mesi fa
loader.py f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 11 mesi fa
metadata.py 78d66f16d1 Chunked Prefill Part 1 (#384) 11 mesi fa
neuron_loader.py f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 11 mesi fa
outlines_decoding.py 0b35176089 feat: add context-free grammars (#376) 11 mesi fa
outlines_logits_processors.py 0b35176089 feat: add context-free grammars (#376) 11 mesi fa
sampling_metadata.py 0634b8a3a6 fix memory pinning conditional 11 mesi fa
utils.py f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 11 mesi fa