Highlights
- Improved the performance of BF16 LLM generation inference: #2253 #2251 #2236 #2278
- Added the optimization for Codegen: #2257
- Provided the dockerfile and updated the related doc to improve the UX for LLM users: #2229 #2195 #2299 #2315 #2283
- Improved the accuracy of the quantization path of LLMs: #2280 #2292 #2275 #2319
- Misc fix and enhancement: #2198 #2264 #2290
Full Changelog: v2.1.0+cpu...v2.1.100+cpu