Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
YangWang92 created a branch on VPTQ/mlc-llm
wy/dev - Universal LLM Deployment Engine with ML Compilation
YangWang92 pushed 13 commits to vptq/eval VPTQ/lm-evaluation-harness
- Add Unitxt Multimodality Support (#2364) * Add Unitxt Multimodality Support Signed-off-by: elronbandel <elronband... 7785577
- Add new tasks to spanish_bench and fix duplicates (#2390) * added tasks to spanish_bench * fixed capitalization i... 7ecee2b
- group to tag for minerva_math (#2404) I find out this bug by comparing the code between hendrycks_math and minerva_m... 624017b
- Fix: Turkish MMLU Regex Pattern (#2393) * Fix Regex Pattern for CoT experiments --------- c1d8795
- fix storycloze datanames (#2409) 9b052fd
- Update prompt (#2421) Update prompt according to: https://github.com/ikergarcia1996/NoticIA/blob/main/prompts.py 389347e
- [Fix] Replace generic exception classes with a more specific ones (#1989) * Replace generic exception classes with a... d4ae963
- Support for IBM watsonx_llm (#2397) * add support for IBM watsonx_llm * add ibm_watsonx_ai package to optional-de... 1185e89
- Fix package extras for watsonx support (#2426) * Update pyproject.toml with watsonx package extra Signed-off-by: ... 7882043
- Fix lora requests when dp with vllm (#2433) * fix: use lora_request for data parallel vllm evals * fix(docs): inc... 838a3e0
- Add xquad task (#2435) * Add xquad task * Update general README * Run pre-commit b40a20a
- Add verify_certificate argument to local-completion (#2440) 57272b6
- hack for vptq 03dc423
YangWang92 created a branch on VPTQ/lm-evaluation-harness
vptq/eval - A framework for few-shot evaluation of language models.
YangWang92 created a comment on an issue on microsoft/VPTQ
> > Hi [@huangtingwei9988](https://github.com/huangtingwei9988), thank you for your interest in our method. > > The Hessian matrix can be collected through quip-sharp (here is my fork, which includ...
YangWang92 opened an issue on microsoft/VPTQ
Huggingface Transformer Support
Huggingface Transformer Support
YangWang92 closed an issue on microsoft/VPTQ
Docker image for development
Hi, are there plans to create a docker image for development / testing, especially for the `algorithm` branch where one might have needs to quantize a customized LLM.
YangWang92 created a comment on an issue on microsoft/VPTQ
> I’ve been trying to run VPTQ in CPU-only mode following the instructions provided. However, I encountered an issue where the `fast_gemv` function appears to require CUDA as well, preventing the m...
YangWang92 created a comment on an issue on microsoft/VPTQ
Hi @huangtingwei9988, thank you for your interest in our method. The Hessian matrix can be collected through quip-sharp (here is my fork, which includes some minor fixes): https://github.com/Yang...