ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
active 2024-06-11 → 2025-10-20 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 497 days from 2024-06-11 to 2025-10-20. Pushes: 24 total, peak 9 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 6 total, peak 2 in a day. Comments: 9 total, peak 2 in a day. Stars: 103 total, peak 10 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
Recent activity
Latest issues, pull requests and releases
- Issue comment#3xlim19962024-10-11 14:04Question regarding bit allocation
- Issue#8xlim19962024-10-11 13:56How to Use ShiftAddLLM During Inference? Unable to Find Relevant Code
- Issue#7xlim19962024-10-11 13:17unable to create a conda environment
- Issue#7xlim19962024-10-10 20:34unable to create a conda environment
- Issue comment#5viraatdas2024-09-23 02:58Fixing error in running BCQ for model/llama
- Pull request#5viraatdas2024-09-23 02:58
- Issue comment#5viraatdas2024-09-07 10:03Fixing error in running BCQ for model/llama
- Issue comment#4viraatdas2024-09-07 10:03Error: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0!
- Issue comment#4viraatdas2024-09-03 00:09Error: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0!
- Issue comment#4Klevente122024-09-03 00:06Error: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0!
- Issue#4viraatdas2024-09-03 00:06Error: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0!
- Issue comment#2w32zhong2024-08-29 16:03Error running ShiftAddLLM/Llama-2-70b-wbits2-acc
- Issue comment#2coco-alen2024-08-16 06:58Error running ShiftAddLLM/Llama-2-70b-wbits2-acc
- Issue comment#2coco-alen2024-08-16 06:58Error running ShiftAddLLM/Llama-2-70b-wbits2-acc
- Issue#2viraatdas2024-08-10 04:58Error running ShiftAddLLM/Llama-2-70b-wbits2-acc
- Issue#1radna02024-06-19 11:25Does it work for training from scratch?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 103 stars here means stars gained during the window, not the repo's star count.