Coverage for  / home / jenkins / .local / lib / python3.10 / site-packages / hyper_parallel / infer / __init__.py: 0%

1# Copyright 2026 Huawei Technologies Co., Ltd 

2# 

3# Licensed under the Apache License, Version 2.0 (the "License"); 

4# you may not use this file except in compliance with the License. 

5# You may obtain a copy of the License at 

6# 

7# http://www.apache.org/licenses/LICENSE-2.0 

8# 

9# Unless required by applicable law or agreed to in writing, software 

10# distributed under the License is distributed on an "AS IS" BASIS, 

11# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 

12# See the License for the specific language governing permissions and 

13# limitations under the License. 

14# ============================================================================ 

15"""Autoregressive generation utilities.""" 

16 

17from hyper_parallel.infer.generation import generate 

18from hyper_parallel.infer.kv_cache import ( 

19 ContextParallelKVCache, 

20 KVCache, 

21 SequenceShardInfo, 

22 get_sequence_shard_info, 

23 shard_past_key_values, 

24) 

25from hyper_parallel.infer.mixin import GenerateMixin 

26from hyper_parallel.infer.sampler import ( 

27 apply_repetition_penalty, 

28 greedy_sample, 

29 sample_next_token, 

30 top_k_sample, 

31 top_p_sample, 

32) 

33from hyper_parallel.infer.utils import ( 

34 GenerationConfig, 

35 apply_logits_processors, 

36 build_causal_mask, 

37 build_position_ids, 

38 gather_context_parallel_logits, 

39 gather_tensor_parallel_logits, 

40 prepare_logits_for_sampling, 

41 should_stop_generation, 

42) 

43 

44__all__ = [ 

45 "GenerationConfig", 

46 "GenerateMixin", 

47 "KVCache", 

48 "ContextParallelKVCache", 

49 "SequenceShardInfo", 

50 "apply_logits_processors", 

51 "apply_repetition_penalty", 

52 "build_causal_mask", 

53 "build_position_ids", 

54 "gather_context_parallel_logits", 

55 "gather_tensor_parallel_logits", 

56 "get_sequence_shard_info", 

57 "generate", 

58 "greedy_sample", 

59 "prepare_logits_for_sampling", 

60 "sample_next_token", 

61 "shard_past_key_values", 

62 "should_stop_generation", 

63 "top_k_sample", 

64 "top_p_sample", 

65]