Minference

What's Changed
* Feature(MInference): support LLaMA-3-70B-1M and multi-gpu PP by iofu728 in https://github.com/microsoft/MInference/pull/59
* Fix(MInference): fix e2e benchmark guideline & fix A-shape multi gpu by iofu728 in https://github.com/microsoft/MInference/pull/66
* Fix(MInference): fix the vs pattern loss / sqrt(dk) by PiotrNawrot in https://github.com/microsoft/MInference/pull/70


**Full Changelog**: https://github.com/microsoft/MInference/compare/v0.1.5...v0.1.5.post1

What's Changed 27
* add vllm>=0.4.1 by liyucheng09 in https://github.com/microsoft/MInference/pull/19, https://github.com/microsoft/MInference/pull/44
* Feature(MInference): update HF demo information, thanks AK's sponsoring by iofu728 in https://github.com/microsoft/MInference/pull/22
* Feature(MInference): add unittest by iofu728 in https://github.com/microsoft/MInference/pull/31, https://github.com/microsoft/MInference/pull/32
* Feature(MInference): add triton-based decoding in case flash_attn is not available by liyucheng09 in https://github.com/microsoft/MInference/pull/35
* Feature(MInference): add e2e benchmark using vllm by iofu728 in https://github.com/microsoft/MInference/pull/49
* Feature(MInference): support llama 3.1 by iofu728 in https://github.com/microsoft/MInference/pull/54
* Hotfix(MInference): fix the import warnings, fix the apply_rotary_pos… by iofu728 in https://github.com/microsoft/MInference/pull/30

New Contributors
* liyucheng09 made their first contribution in https://github.com/microsoft/MInference/pull/19

**Full Changelog**: https://github.com/microsoft/MInference/compare/v0.1.4...v0.1.5

What's Changed
* Hotfix(MInference): fix vllm>=0.4.1 by iofu728 in https://github.com/microsoft/MInference/pull/44

**Full Changelog**: https://github.com/microsoft/MInference/compare/v0.1.4.post3...v0.1.4.post4

What's Changed
* Feature(MInference): add triton-based decoding in case flash_attn is not available by liyucheng09 in https://github.com/microsoft/MInference/pull/35

**Full Changelog**: https://github.com/microsoft/MInference/compare/v0.1.4.post2...v0.1.4.post3

What's Changed
* Feature(MInference): update HF demo information, thanks AK's sponsoring by iofu728 in https://github.com/microsoft/MInference/pull/22
* Feature(MInference): remove pycuda; 20
* Feature(MInference): support multi-gpu; 25
* Feature(MInference): add unittest by iofu728 in https://github.com/microsoft/MInference/pull/31 https://github.com/microsoft/MInference/pull/32

- Fixes 28 the import warnings;
- Fixed 25 fix the apply_rotary_pos_emb_single;
- Fixed phi-3 vs kernel;

**Full Changelog**: https://github.com/microsoft/MInference/compare/v0.1.4.post1...v0.1.4.post2

What's Changed
* add vllm support for 0.4.2 and 0.4.3 by liyucheng09 in https://github.com/microsoft/MInference/pull/19

New Contributors
* liyucheng09 made their first contribution in https://github.com/microsoft/MInference/pull/19

**Full Changelog**: https://github.com/microsoft/MInference/compare/v0.1.4...v0.1.4.post1