Skip to content

PrismAI/Bonsai Model Support (inference only)#2640

Merged
Qubitium merged 13 commits intomainfrom
prism
Apr 1, 2026
Merged

PrismAI/Bonsai Model Support (inference only)#2640
Qubitium merged 13 commits intomainfrom
prism

Conversation

@Qubitium
Copy link
Copy Markdown
Collaborator

@Qubitium Qubitium commented Apr 1, 2026

requires HF transformers PR/patch: huggingface/transformers#45157

Comment thread gptqmodel/nn_modules/qlinear/gemm_awq.py Fixed
Comment thread gptqmodel/nn_modules/qlinear/gemm_awq.py Fixed
Comment thread gptqmodel/utils/hf.py Dismissed
Comment thread gptqmodel/utils/hf.py Dismissed
Qubitium added 2 commits April 1, 2026 05:31
# Conflicts:
#	gptqmodel/nn_modules/qlinear/gemm_awq.py
#	gptqmodel/nn_modules/qlinear/gemv_awq.py
#	gptqmodel/nn_modules/qlinear/paroquant.py
#	gptqmodel/utils/awq.py
#	gptqmodel/utils/paroquant.py
#	gptqmodel_ext/awq/torch_bind.cpp
#	scripts/benchmark_awq_cuda_fp32_reduce_ab.py
#	scripts/benchmark_awq_fused_reduce_ab.py
#	scripts/benchmark_paroquant_rotation_cache_ab.py
#	scripts/benchmark_paroquant_runtime_cache_ab.py
#	scripts/profile_paroquant_runtime_cache_case.py
#	tests/kernels/test_awq_cuda_fp32_reduce.py
#	tests/test_paroquant.py
@Qubitium Qubitium merged commit 519d642 into main Apr 1, 2026
6 checks passed
@Qubitium Qubitium deleted the prism branch April 1, 2026 07:54
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant