Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / TimDettmers/bitsandbytes issues and pull requests
#1260 - bitsandbytes broken with regards to cuda with name error 'str2optimizer32bit' and name 'str2optimizer8bit_blockwise' is not defined
Issue -
State: open - Opened by artsera 5 months ago
#1259 - Fixed tests for cpu only platforms
Pull Request -
State: open - Opened by galqiwi 5 months ago
- 1 comment
#1258 - error message not meaningful enough — why is it looking in folders that are not in my path and are unrelated environment variables?
Issue -
State: open - Opened by ClaireCJS 5 months ago
- 2 comments
#1257 - Add xpu support for 4bit (nf4/fp4) and 8bit quantization
Pull Request -
State: open - Opened by zhuhong61 5 months ago
- 2 comments
#1256 - [QUESTION] Quantizing in a different way...
Issue -
State: open - Opened by 0wwafa 5 months ago
#1255 - Create build job for ROCm
Pull Request -
State: open - Opened by pnunna93 5 months ago
- 1 comment
#1254 - AssertionError: Torch not compiled with CUDA enabled
Issue -
State: open - Opened by alexgit256 5 months ago
- 2 comments
#1253 - Bump the minor-patch group across 1 directory with 2 updates
Pull Request -
State: closed - Opened by dependabot[bot] 5 months ago
- 1 comment
Labels: dependencies
#1252 - LLama3-8B - FSDP + QLORA results in OOM with 4 A40's
Issue -
State: closed - Opened by MikaSie 5 months ago
- 1 comment
#1251 - CPU/XPU: disable torch.compile if g++ is not available
Pull Request -
State: open - Opened by Xia-Weiwen 5 months ago
- 10 comments
#1250 - Conda (forge) recipe
Issue -
State: closed - Opened by tvatter 5 months ago
#1249 - Fail to use zero_init to construct llama2 with deepspeed zero3 and bnb!
Issue -
State: open - Opened by CHNRyan 5 months ago
#1248 - need a nice installation
Issue -
State: closed - Opened by JohnHerry 5 months ago
- 6 comments
#1247 - Bump pytest from 8.2.1 to 8.2.2 in the minor-patch group
Pull Request -
State: closed - Opened by dependabot[bot] 5 months ago
- 2 comments
Labels: dependencies
#1246 - "You have a version of `bitsandbytes` that is not compatible with 4bit inference and training"
Issue -
State: open - Opened by entzyeung 5 months ago
- 7 comments
#1245 - ROCm and 8-bit quantization
Issue -
State: open - Opened by DavideRossi 5 months ago
- 4 comments
#1244 - cleanup docs-build breaking install instructs
Pull Request -
State: closed - Opened by Titus-von-Koeller 5 months ago
- 5 comments
#1243 - provide temp flag for outside libs to detect multi-backend preview
Pull Request -
State: closed - Opened by Titus-von-Koeller 5 months ago
#1242 - NotImplementedError: igemmlt not available (probably built with NO_CUBLASLT)
Issue -
State: closed - Opened by stevenmanton 5 months ago
- 2 comments
#1241 - Return MPS compiled library in `get_native_library()`
Pull Request -
State: open - Opened by sealad886 5 months ago
- 3 comments
#1240 - Revert "Add `"lamb"` to `str2optimizer32bit`"
Pull Request -
State: closed - Opened by younesbelkada 5 months ago
- 5 comments
#1238 - CPU: add torch.compile for F.double_quant and F.quantize_4bit
Pull Request -
State: closed - Opened by Xia-Weiwen 5 months ago
- 5 comments
#1237 - RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument mat2 in method wrapper_CUDA_mm)
Issue -
State: open - Opened by kevalshah90 6 months ago
- 2 comments
#1236 - load_in_8bit hangs on ROCm
Issue -
State: open - Opened by DavideRossi 6 months ago
- 3 comments
#1235 - out kwarg in matmul_4bit() is not working
Issue -
State: open - Opened by chenqianfzh 6 months ago
- 3 comments
#1234 - OSError: libcusparse.so.11: cannot open shared object file: No such file or directory CUDA Setup failed despite CUDA being available.
Issue -
State: open - Opened by Aashi779 6 months ago
#1233 - Is it possible to enable fused op F.gemv_4bit in F.gemv_4bit backward?
Issue -
State: open - Opened by jiqing-feng 6 months ago
- 1 comment
#1232 - "Only Tensors of floating point and complex dtype can require gradients", on FSDP, Accelerate, quatization
Issue -
State: closed - Opened by artkpv 6 months ago
- 3 comments
#1231 - FIX Make Int8Params deepcopy-able
Pull Request -
State: closed - Opened by BenjaminBossan 6 months ago
- 2 comments
#1230 - FIX_ Prevent __getstate__ from mutating Params4bit
Pull Request -
State: closed - Opened by BenjaminBossan 6 months ago
- 4 comments
#1229 - 8bit CAME optimizer
Issue -
State: open - Opened by betterftr 6 months ago
#1228 - fix blocksize
Pull Request -
State: closed - Opened by jiqing-feng 6 months ago
#1227 - cpu install guide
Pull Request -
State: closed - Opened by jiqing-feng 6 months ago
- 14 comments
#1226 - Request for AdamW8bit support on CPU (would help TorchTune)
Issue -
State: open - Opened by sanchitintel 6 months ago
- 5 comments
Labels: INTEL integration, cross-platform
#1225 - Error invalid device ordinal at line 359 in file /opt/bitsandbytes/csrc/pythonInterface.c
Issue -
State: open - Opened by shahizat 6 months ago
#1224 - Bump scipy from 1.13.0 to 1.13.1 in the minor-patch group
Pull Request -
State: closed - Opened by dependabot[bot] 6 months ago
- 1 comment
Labels: dependencies
#1223 - Add empty stubs for Ascend NPU
Pull Request -
State: closed - Opened by statelesshz 6 months ago
- 1 comment
#1222 - Add `"lamb"` to `str2optimizer32bit`
Pull Request -
State: closed - Opened by EtienneDosSantos 6 months ago
- 6 comments
#1221 - Exact version match required between the system and PyTorch CUDA libraries for the compilation to succeed
Issue -
State: open - Opened by mirekphd 6 months ago
- 1 comment
#1220 - (WIP) Multi backend refactor -> main (full diff of all already merged PRs)
Pull Request -
State: open - Opened by Titus-von-Koeller 6 months ago
#1218 - please provide python whel package in nvidia jetson agx orin (aarch64 + cuda)
Issue -
State: open - Opened by WangFengtu1996 6 months ago
- 1 comment
#1217 - Error in Windows
Issue -
State: open - Opened by jeetendraabvv 6 months ago
- 2 comments
#1216 - Bump pytest from 8.2.0 to 8.2.1 in the minor-patch group
Pull Request -
State: closed - Opened by dependabot[bot] 6 months ago
- 1 comment
Labels: dependencies
#1215 - Update matplotlib requirement from ~=3.8.4 to ~=3.9.0 in the major group
Pull Request -
State: closed - Opened by dependabot[bot] 6 months ago
- 1 comment
Labels: dependencies
#1214 - RuntimeError: Something when wrong when trying to find file. Maybe you do not have a linux system?
Issue -
State: open - Opened by fantasy-fish 6 months ago
- 1 comment
#1212 - Could not load bitsandbytes native library: 'NoneType' object has no attribute 'split'
Issue -
State: closed - Opened by jcalvoch 6 months ago
- 1 comment
#1211 - [docs] Clarify FSDP-QLoRA
Pull Request -
State: closed - Opened by stevhliu 6 months ago
- 3 comments
#1210 - AttributeError: 'NoneType' object has no attribute 'cquantize_blockwise_fp16_nf4'
Issue -
State: open - Opened by wissamee 6 months ago
- 5 comments
#1209 - AnimateDiff SDXL won't run
Issue -
State: open - Opened by idesign2018 6 months ago
#1208 - undefined symbol: cdequantize_blockwise_fp32
Issue -
State: open - Opened by Littleiii 6 months ago
- 1 comment
#1207 - BitsandBytes Enablement on ROCm
Pull Request -
State: closed - Opened by pnunna93 6 months ago
- 6 comments
#1206 - Support 4bit on CPU backend
Pull Request -
State: closed - Opened by Xia-Weiwen 6 months ago
- 5 comments
#1205 - problem with loading my finetuned Llama2 model - type object 'Params4bit' has no attribute 'from_prequantized'
Issue -
State: open - Opened by lujain89 6 months ago
- 3 comments
#1204 - RuntimeError: CUDA Setup failed despite GPU being available. Please run the following command to get more information:
Issue -
State: open - Opened by Worromots 6 months ago
- 3 comments
#1203 - Mistral-v0.1 nf4 is not quantized into 4bit
Issue -
State: open - Opened by LameloBally 6 months ago
- 1 comment
#1202 - AttributeError: 'NoneType' object has no attribute 'split' CUDA Setup failed despite CUDA being available.
Issue -
State: open - Opened by GoDJr 6 months ago
- 1 comment
#1201 - PicklingError: Can't pickle <function Embedding.forward at XXXXXXX> it's not the same object as torch.nn.modules.sparse.Embedding.forward
Issue -
State: open - Opened by arpit2665 6 months ago
#1200 - Could not run Kohya
Issue -
State: open - Opened by hapuku1552 6 months ago
#1199 - bitsandbytes import error in colab
Issue -
State: open - Opened by ss8101 6 months ago
- 1 comment
#1198 - CONTRIBUTING.md references Meta CLA
Issue -
State: closed - Opened by littledan 6 months ago
- 1 comment
#1197 - fix doc builder workflow by reverting to old image
Pull Request -
State: closed - Opened by Titus-von-Koeller 6 months ago
- 2 comments
#1196 - WIP: test docs pr workflow (sth about a missing dependency)
Pull Request -
State: closed - Opened by Titus-von-Koeller 6 months ago
- 1 comment
#1195 - (WIP) Multi platform abstraction tweaks
Pull Request -
State: open - Opened by Titus-von-Koeller 6 months ago
- 2 comments
Labels: high priority, cross-platform
#1194 - error on VectorstoreIndexCreator
Issue -
State: open - Opened by MohammadAminDHM 6 months ago
- 7 comments
#1193 - Bug issues
Issue -
State: open - Opened by neuro-nest-ai 7 months ago
#1192 - Bump the minor-patch group with 2 updates
Pull Request -
State: closed - Opened by dependabot[bot] 7 months ago
- 1 comment
Labels: dependencies
#1191 - bitsandbytes interprets URLs from environment variables as paths
Issue -
State: open - Opened by allo- 7 months ago
- 2 comments
#1190 - CUDA Setup failed despite CUDA being Available :: NameError: name 'str2optimizer32bit' is not defined
Issue -
State: open - Opened by NavinKumarMNK 7 months ago
- 4 comments
#1189 - NameError: name 'str2optimizer32bit' is not defined
Issue -
State: open - Opened by Sakurakdx 7 months ago
- 3 comments
#1188 - TESTS: add `is_flaky` decorator on flaky tests
Pull Request -
State: open - Opened by younesbelkada 7 months ago
- 2 comments
#1187 - Fixed optim update error with non-contiguous grads/params
Pull Request -
State: open - Opened by Edenzzzz 7 months ago
#1186 - Quantized model using load_in_8bit produces very different results on T4 vs V100 GPU on Colab
Issue -
State: open - Opened by cjiangz 7 months ago
#1185 - 32 bit optimizer update error despite gradients being the same
Issue -
State: open - Opened by Edenzzzz 7 months ago
- 4 comments
#1184 - torch compile support?
Issue -
State: open - Opened by stillmatic 7 months ago
- 1 comment
Labels: torch.compile
#1183 - (docs) integrations: fix omission in bf16 related warning
Pull Request -
State: closed - Opened by Titus-von-Koeller 7 months ago
- 2 comments
#1182 - Update pandas requirement from ~=2.2.1 to ~=2.2.2 in the major group
Pull Request -
State: closed - Opened by dependabot[bot] 7 months ago
- 1 comment
Labels: dependencies
#1181 - fix min_8bit_size ignored bug
Pull Request -
State: open - Opened by Edenzzzz 7 months ago
#1180 - NameError: name 'str2optimizer32bit' is not defined
Issue -
State: open - Opened by sage-khan 7 months ago
- 2 comments
#1179 - TypeError: Input tensors need to be on the same GPU, but found the following tensor and device combinations
Issue -
State: open - Opened by rlanday 7 months ago
- 1 comment
#1178 - Add int8 ops for CPU
Pull Request -
State: closed - Opened by Xia-Weiwen 7 months ago
- 19 comments
#1177 - [QUESTION] does setting load_in_4bit=True use w4a4, w4a8 or w4a16 ?
Issue -
State: open - Opened by AbhinavDutta 7 months ago
#1175 - bitsandbytes cuda library error
Issue -
State: closed - Opened by parksez 7 months ago
- 1 comment
#1174 - HTTP ERROR 403. It says: 127.0.0.1 refused^
Issue -
State: closed - Opened by HowKing66 7 months ago
- 1 comment
#1173 - Stub out additional backends
Pull Request -
State: closed - Opened by matthewdouglas 7 months ago
- 3 comments
#1172 - CUDA Setup failed despite GPU being available.
Issue -
State: open - Opened by bryanhughes 7 months ago
- 4 comments
#1171 - Add CUDA 12.4 to Linux x86-64 Build Workflow
Pull Request -
State: closed - Opened by matthewdouglas 7 months ago
- 2 comments
#1170 - Bump scipy from 1.12.0 to 1.13.0 in the minor-patch group
Pull Request -
State: closed - Opened by dependabot[bot] 7 months ago
- 1 comment
Labels: dependencies
#1169 - Update matplotlib requirement from ~=3.8.3 to ~=3.8.4 in the major group
Pull Request -
State: closed - Opened by dependabot[bot] 7 months ago
- 1 comment
Labels: dependencies
#1168 - Path is broken in Stable Diffusion after installing extension.
Issue -
State: open - Opened by vicbanta 7 months ago
#1166 - AttributeError: module 'bitsandbytes' has no attribute 'nn'
Issue -
State: open - Opened by Harsh-raj 8 months ago
- 4 comments
#1165 - Stochastic rounding support for 8-bit optimizers
Issue -
State: open - Opened by drhead 8 months ago
- 1 comment
#1164 - [`Core`] Change 8-bit serialization weight format format
Pull Request -
State: closed - Opened by younesbelkada 8 months ago
- 5 comments
#1162 - Bump the minor-patch group with 1 update
Pull Request -
State: closed - Opened by dependabot[bot] 8 months ago
- 1 comment
Labels: dependencies
#1161 - Quantizing models with bitsandbytes
Issue -
State: closed - Opened by raunaks13 8 months ago
#1160 - Fix 4bit quantization with blocksize = 4096
Pull Request -
State: closed - Opened by matthewdouglas 8 months ago
- 3 comments
#1157 - Tensor support for quantize_nf4
Issue -
State: closed - Opened by YLGH 8 months ago
- 1 comment
#1156 - Win&cuda12.1
Issue -
State: open - Opened by bobshen0721 8 months ago
#1155 - DBRX Support
Issue -
State: open - Opened by maziyarpanahi 8 months ago
- 4 comments
#1154 - NVIDIA TX2+jetpack 5+Ubuntu20.4: CUDA Setup failed despite GPU being available
Issue -
State: closed - Opened by qxpBlog 8 months ago
- 2 comments