17
43
Version | Commit message | Commit author | Last scanned | ||
|---|---|---|---|---|---|
| transformers>=4.44.2, backward compat | itlevy | Never scanned | |||
| v4.45 support (#6) | itlevy | Nov 12, 2024 | |||
| v4.46 support (#7) | itlevy | Nov 12, 2024 | |||
| nvidia-open-model-license (#14) | itlevy | Nov 12, 2024 | |||
| add batch_size attribute to VariableCache (#15) | itlevy | Never scanned | |||
| DeciLMForCausalLM(DeciLMPreTrainedModel, GenerationMixin) for v4.50 (#16) | itlevy | Nov 12, 2024 | |||
| fixed cache over-alloc bug (#17) | abercovich | Oct 20, 2024 | |||
| Patching hf bug that creates wrong cache length if only inputs_embeds are passed to the model (#19) | itlevy | Never scanned | |||
| Patching hf bug that creates wrong cache length if only inputs_embeds are passed to the model (#19) | itlevy, tomer-nv | Oct 18, 2024 | |||
| add batch_size attribute to VariableCache | itlevy | Oct 22, 2024 | |||
| fixed cache over-alloc bug | tomer-nv | Oct 28, 2024 | |||
| Update README.md | Vlad748283847 | Nov 7, 2024 | |||
| v4.46 support | itlevy | Nov 10, 2024 | |||
| Patching hf bug that creates wrong cache length if only inputs_embeds are passed to the model | tomer-nv | Nov 12, 2024 | |||
| v4.45 support | itlevy | Nov 12, 2024 | |||
| nvidia-open-model-license | itlevy | Nov 12, 2024 | |||
| nvidia-open-model-license | itlevy | Nov 12, 2024 | |||