LLMs Inference Papers Versions Save

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

v0.7

3 weeks ago

What's Changed

LLMLingua-2 by @liyucheng09 in https://github.com/DefTruth/Awesome-LLM-Inference/pull/11
add SnapKV by @liyucheng09 in https://github.com/DefTruth/Awesome-LLM-Inference/pull/12
Add Microbenchmark by @Miroier in https://github.com/DefTruth/Awesome-LLM-Inference/pull/14
[KVcache] add "Gear" paper and code of "Keyformer" by @HarryWu-CHN in https://github.com/DefTruth/Awesome-LLM-Inference/pull/13
Update README.md by @preminstrel in https://github.com/DefTruth/Awesome-LLM-Inference/pull/15

New Contributors

@Miroier made their first contribution in https://github.com/DefTruth/Awesome-LLM-Inference/pull/14
@HarryWu-CHN made their first contribution in https://github.com/DefTruth/Awesome-LLM-Inference/pull/13
@preminstrel made their first contribution in https://github.com/DefTruth/Awesome-LLM-Inference/pull/15

Full Changelog: https://github.com/DefTruth/Awesome-LLM-Inference/compare/v0.6...v0.7

v0.6

1 month ago

What's Changed

Add an ICLR paper for KV cache compression by @Janghyun1230 in https://github.com/DefTruth/Awesome-LLM-Inference/pull/8
Add github link for paper FP8-Quantization[2208.09225] by @Mr-Philo in https://github.com/DefTruth/Awesome-LLM-Inference/pull/9

New Contributors

@Janghyun1230 made their first contribution in https://github.com/DefTruth/Awesome-LLM-Inference/pull/8
@Mr-Philo made their first contribution in https://github.com/DefTruth/Awesome-LLM-Inference/pull/9

Full Changelog: https://github.com/DefTruth/Awesome-LLM-Inference/compare/v0.5...v0.6

v0.5

1 month ago

What's Changed

correct affiliation error by @liyucheng09 in https://github.com/DefTruth/Awesome-LLM-Inference/pull/3
fix typo by @lkm2835 in https://github.com/DefTruth/Awesome-LLM-Inference/pull/6
add context compression & new papers KV compression by @liyucheng09 in https://github.com/DefTruth/Awesome-LLM-Inference/pull/7

New Contributors

@liyucheng09 made their first contribution in https://github.com/DefTruth/Awesome-LLM-Inference/pull/3
@lkm2835 made their first contribution in https://github.com/DefTruth/Awesome-LLM-Inference/pull/6

Full Changelog: https://github.com/DefTruth/Awesome-LLM-Inference/compare/v0.4...v0.5

v0.4

2 months ago

v0.3

5 months ago

v0.2

7 months ago

更新精简版LLMs推理论文集PDF

v0.1

8 months ago

LLMs-Open-Papers-as-Book-v0.1_For-Beginners