bitsandbytes-foundation bitsandbytes issues

bitsandbytes-foundation / bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

https://huggingface.co/docs/bitsandbytes/main/en/index

MIT License

6.31k stars 634 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Release 0.44.0 does not belong to the current repository

#1370 ccoulombe closed 1 month ago
2
Add workflow to publish tagged releases to PyPI

#1369 matthewdouglas closed 1 month ago
1
Update pandas requirement from ~=2.2.2 to ~=2.2.3 in the major group

#1368 dependabot[bot] closed 1 month ago
2
Enable packaging for ROCm 6.2

#1367 pnunna93 closed 2 months ago
1
cpu benchmark

#1366 jiqing-feng closed 2 months ago
1
Change 8bit optimizer blocksize 2048->256; additional bf16 support

#1365 matthewdouglas closed 2 months ago
2
RuntimeError: CUDA error: CUBLAS_STATUS_NOT_SUPPORTED when calling cublasGemmEx

#1363 LukeLIN-web opened 2 months ago
1
Bump the minor-patch group with 3 updates

#1362 dependabot[bot] closed 2 months ago
0
Update matplotlib requirement from ~=3.9.1 to ~=3.9.2 in the major group

#1361 dependabot[bot] closed 2 months ago
0
Add AdEMAMix optimizer

#1360 matthewdouglas closed 2 months ago
1
Merge LoRA into 405B

#1359 junzhang-zj opened 2 months ago
4
check grad before using ipex

#1358 jiqing-feng closed 2 months ago
1
Nf4 grad

#1357 jiqing-feng closed 2 months ago
0
Lion Optimizer With Triton Kernel

#1356 lapp0 closed 2 months ago
1
cuda is available but import bnb error

#1355 ZeroneBo opened 2 months ago
2
Model not able to quantize

#1354 alielfilali01 opened 2 months ago
0
add CPU benchmark

#1353 jiqing-feng closed 2 months ago
1
docs: add internal reference to multi-backend guide

#1352 Titus-von-Koeller closed 2 months ago
1
docs: add internal reference to multi-backend guide

#1351 Titus-von-Koeller closed 2 months ago
1
Bug when using optimizer LAMB 32bits

#1350 FrsECM opened 2 months ago
0
fix nf4 memory issue by init op_context in forward

#1349 jiqing-feng closed 2 months ago
3
Nf4 reload

#1348 jiqing-feng closed 2 months ago
1
Torch autograd support for dequantize methods

#1347 yaldashbz opened 2 months ago
0
Bump the minor-patch group with 2 updates

#1346 dependabot[bot] closed 2 months ago
2
Update matplotlib requirement from ~=3.9.1 to ~=3.9.2 in the major group

#1345 dependabot[bot] closed 2 months ago
2
Add `move_to_device` kwarg to the optimizer's `load_state_dict`

#1344 koute closed 2 months ago
1
Cannot load decoder.lm_head.weight when loading 4 bit quantized model using VisionEncoderDecoder.from_pretrained

#1343 AditiJain14 opened 2 months ago
1
quantize_4bit/dequantize_4bit gives wrong output on in-contiguous tensor

#1342 chenqianfzh opened 2 months ago
0
Update for VS2022 17.11 compatibility with CUDA < 12.4

#1341 matthewdouglas closed 2 months ago
0
rm warn for multi backend

#1336 jiqing-feng closed 2 months ago
0
Bump the minor-patch group with 2 updates

#1335 dependabot[bot] closed 2 months ago
1
Update matplotlib requirement from ~=3.9.1 to ~=3.9.2 in the major group

#1334 dependabot[bot] closed 2 months ago
1
Update diagnostic functions for ROCm

#1333 pnunna93 closed 2 months ago
5
Linear8bitLt can not be moved back to cpu

#1332 Nerogar opened 3 months ago
2
Pretrained Causal LM cannot be loaded in 4bit/8bit

#1331 adrienchaton opened 3 months ago
6
Enable certain CUDA kernels to accept specified cuda stream

#1330 jeejeelee closed 3 months ago
8
Any plan to support block size 32?

#1329 lllyasviel opened 3 months ago
4
Cuda source cleanup , refactor and fixes

#1328 abhilash1910 closed 2 months ago
4
RuntimeError: Failed to import transformers.integrations.bitsandbytes because of the following error (look up to see its traceback):

#1327 pradeep10kumar opened 3 months ago
1
MPS progress

#1326 tcdent opened 3 months ago
3
fix 4bit dtype

#1325 jiqing-feng closed 3 months ago
1
Error occurred when executing DownloadAndLoadFlorence2Model:

#1324 JunpeakChen closed 3 months ago
1
Error while trying to install the multi-backend-refactor branch for rocm in WSL2

#1323 Kademo15 closed 3 months ago
1
RuntimeError: CUDA Setup failed despite GPU being available. Please run the following command to get more information:

#1322 pradeep10kumar opened 3 months ago
1
'nf4' compute datatype?

#1321 dorsa-zeinali opened 3 months ago
1
where are the outliers stored in LLM.int8 quantization for inference suing transformers library on AMD GPU?

#1320 vbayanag opened 3 months ago
2
About fusion of **kdequantize kernel** and **simple bf16/fp16 matmul**

#1319 Ther-nullptr opened 3 months ago
1
Bugfix: Load correct nocublaslt library variant when BNB_CUDA_VERSION override is set

#1318 matthewdouglas closed 3 months ago
1
Communicate blocksize constraints to kernels that take blocksize as a runtime argument

#1317 mm04926412 opened 3 months ago
6
Initial support for ppc64le

#1316 mgiessing closed 3 months ago
3

Previous Next