File tree Expand file tree Collapse file tree 1 file changed +3
-3
lines changed
Expand file tree Collapse file tree 1 file changed +3
-3
lines changed Original file line number Diff line number Diff line change @@ -176,12 +176,12 @@ jobs:
176176 matrix :
177177 quant :
178178 - name : " non-quantized"
179- artifact : " voxtral -cuda-export"
179+ artifact : " gemma3 -cuda-export"
180180 extra_args : " "
181181 - name : " quantized-int4-tile-packed"
182- artifact : " voxtral -cuda-quantized-int4-tile-packed"
182+ artifact : " gemma3 -cuda-quantized-int4-tile-packed"
183183 extra_args : " --qlinear 4w --qlinear_encoder 4w --qlinear_packing_format tile_packed_to_4d --qlinear_encoder_packing_format tile_packed_to_4d"
184- # TODO: enable int4-weight-only on gemma3.
184+ # TODO: enable int4-weight-only on gemma3.
185185 # - name: "quantized-int4-weight-only"
186186 # artifact: "voxtral-cuda-quantized-int4-weight-only"
187187 # # TODO: adding "--qlinear 4w" produces invalid results. Need further investigation.
You can’t perform that action at this time.
0 commit comments