Skip to content

Commit 95387c8

Browse files
committed
update readme for Intel CPU and XPU do not need make csrc codes
1 parent 314f724 commit 95387c8

File tree

2 files changed

+3
-5
lines changed

2 files changed

+3
-5
lines changed

docs/source/installation.mdx

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -336,8 +336,6 @@ The below commands are for Linux. For installing on Windows, please adapt the be
336336
git clone --depth 1 -b multi-backend-refactor https://github.com/bitsandbytes-foundation/bitsandbytes.git && cd bitsandbytes/
337337
pip install intel_extension_for_pytorch
338338
pip install -r requirements-dev.txt
339-
cmake -DCOMPUTE_BACKEND=cpu -S .
340-
make
341339
pip install -e . # `-e` for "editable" install, when developing BNB (otherwise leave that out)
342340
```
343341

docs/source/non_cuda_backends.mdx

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -33,12 +33,12 @@ The following performance data is collected from Intel 4th Gen Xeon (SPR) platfo
3333

3434
| Data Type | BF16 | INT8 | NF4 | FP4 |
3535
|---|---|---|---|---|
36-
| Speed-Up (vs BF16) | 1.0x | 0.6x | 2.3x | 0.03x |
36+
| Speed-Up (vs BF16) | 1.0x | 0.44x | 1.8x | 0.1x |
3737
| Memory (GB) | 13.1 | 7.6 | 5.0 | 4.6 |
3838

3939
#### Fine-Tuning (CPU)
4040

41-
| Data Type | AMP BF16 | INT8 | NF4 | FP4 |
41+
| Data Type | BF16 | INT8 | NF4 | FP4 |
4242
|---|---|---|---|---|
43-
| Speed-Up (vs AMP BF16) | 1.0x | 0.38x | 0.07x | 0.07x |
43+
| Speed-Up (vs BF16) | 1.0x | 0.38x | 0.1x | 0.1x |
4444
| Memory (GB) | 40 | 9 | 6.6 | 6.6 |

0 commit comments

Comments
 (0)