Skip to content

Remove dead bitsandbytes CxB code from 8-bit inference path #34633

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
vllm-bot merged 1 commit into from
Feb 17, 2026
Merged

Remove dead bitsandbytes CxB code from 8-bit inference path #34633

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 0 additions & 10 deletions vllm/model_executor/layers/quantization/bitsandbytes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -336,16 +336,6 @@ def _apply_8bit_weight(

current_index += output_size

# only update the matmul_states if it is not profile_run
if (
generation > 0
and not self.quant_config.llm_int8_has_fp16_weight
and matmul_states[i].CB is not None
and matmul_states[i].CxB is not None
):
del matmul_states[i].CB
qweight[offsets[i] : offsets[i + 1]] = matmul_states[i].CxB

out = out.to(original_type)

if reshape_after_matmul:
Expand Down