biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

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

Browse Source 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Tim Dettmers
2026-02-17 04:49:14 -05:00
committed by GitHub
parent 1d65283e95
commit d44a5b6c47
1 changed files with 0 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/model_executor/layers/quantization/bitsandbytes.py
View File

@@ -336,16 +336,6 @@ class BitsAndBytesLinearMethod(LinearMethodBase):
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: