Mistral 7b v03 - inference install - wheel error

Hi there, trying to install mistral 7b v03, but i get error trying to install mistral_inference,

Building wheels for collected packages: xformers

Building wheel for xformers (setup.py) … error
error: subprocess-exited-with-error

× python setup.py bdist_wheel did not run successfully.
│ exit code: 1
╰─> [636 lines of output]
fatal: not a git repository (or any of the parent directories): .git
running bdist_wheel
running build
running build_py
creating build\lib.win-amd64-cpython-310\xformers
copying xformers\attn_bias_utils.py → build\lib.win-amd64-cpython-310\xformers
copying xformers\checkpoint.py → build\lib.win-amd64-cpython-310\xformers
copying xformers\info.py → build\lib.win-amd64-cpython-310\xformers
copying xformers\test.py → build\lib.win-amd64-cpython-310\xformers
copying xformers\utils.py → build\lib.win-amd64-cpython-310\xformers
copying xformers_cpp_lib.py → build\lib.win-amd64-cpython-310\xformers
copying xformers_deprecation_warning.py → build\lib.win-amd64-cpython-310\xformers
copying xformers_init_.py → build\lib.win-amd64-cpython-310\xformers
creating build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\benchmark_attn_decoding.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\benchmark_core.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\benchmark_indexing.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\benchmark_mem_eff_attention.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\benchmark_merge_attentions.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\benchmark_multi_head_dispatch.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\benchmark_nystrom_utils.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\benchmark_revnet.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\benchmark_sddmm.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\benchmark_sequence_parallel_fused.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\benchmark_sp24.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\benchmark_swiglu.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\benchmark_tiled_matmul.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks\utils.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
copying xformers\benchmarks_init_.py → build\lib.win-amd64-cpython-310\xformers\benchmarks
creating build\lib.win-amd64-cpython-310\xformers\components
copying xformers\components\activations.py → build\lib.win-amd64-cpython-310\xformers\components
copying xformers\components\input_projection.py → build\lib.win-amd64-cpython-310\xformers\components
copying xformers\components\multi_head_dispatch.py → build\lib.win-amd64-cpython-310\xformers\components
copying xformers\components\patch_embedding.py → build\lib.win-amd64-cpython-310\xformers\components
copying xformers\components\residual.py → build\lib.win-amd64-cpython-310\xformers\components
copying xformers\components\reversible.py → build\lib.win-amd64-cpython-310\xformers\components
copying xformers\components\simplicial_embedding.py → build\lib.win-amd64-cpython-310\xformers\components
copying xformers\components_init_.py → build\lib.win-amd64-cpython-310\xformers\components
creating build\lib.win-amd64-cpython-310\xformers\factory
copying xformers\factory\block_configs.py → build\lib.win-amd64-cpython-310\xformers\factory
copying xformers\factory\block_factory.py → build\lib.win-amd64-cpython-310\xformers\factory
copying xformers\factory\hydra_helper.py → build\lib.win-amd64-cpython-310\xformers\factory
copying xformers\factory\model_factory.py → build\lib.win-amd64-cpython-310\xformers\factory
copying xformers\factory\weight_init.py → build\lib.win-amd64-cpython-310\xformers\factory
copying xformers\factory_init_.py → build\lib.win-amd64-cpython-310\xformers\factory
creating build\lib.win-amd64-cpython-310\xformers\helpers
copying xformers\helpers\hierarchical_configs.py → build\lib.win-amd64-cpython-310\xformers\helpers
copying xformers\helpers\test_utils.py → build\lib.win-amd64-cpython-310\xformers\helpers
copying xformers\helpers\timm_sparse_attention.py → build\lib.win-amd64-cpython-310\xformers\helpers
copying xformers\helpers_init_.py → build\lib.win-amd64-cpython-310\xformers\helpers
creating build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops\common.py → build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops\differentiable_collectives.py → build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops\indexing.py → build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops\ipc.py → build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops\modpar_layers.py → build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops\rmsnorm.py → build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops\rope_padded.py → build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops\seqpar.py → build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops\sequence_parallel_fused_ops.py → build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops\sp24.py → build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops\swiglu_op.py → build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops\tiled_matmul.py → build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops\unbind.py → build\lib.win-amd64-cpython-310\xformers\ops
copying xformers\ops_init_.py → build\lib.win-amd64-cpython-310\xformers\ops
creating build\lib.win-amd64-cpython-310\xformers\profiler
copying xformers\profiler\api.py → build\lib.win-amd64-cpython-310\xformers\profiler
copying xformers\profiler\device_limits.py → build\lib.win-amd64-cpython-310\xformers\profiler
copying xformers\profiler\find_slowest.py → build\lib.win-amd64-cpython-310\xformers\profiler
copying xformers\profiler\profiler.py → build\lib.win-amd64-cpython-310\xformers\profiler
copying xformers\profiler\profiler_dcgm.py → build\lib.win-amd64-cpython-310\xformers\profiler
copying xformers\profiler\profiler_dcgm_impl.py → build\lib.win-amd64-cpython-310\xformers\profiler
copying xformers\profiler\profile_analyzer.py → build\lib.win-amd64-cpython-310\xformers\profiler
copying xformers\profiler_init_.py → build\lib.win-amd64-cpython-310\xformers\profiler
creating build\lib.win-amd64-cpython-310\xformers\sparse
copying xformers\sparse\blocksparse_tensor.py → build\lib.win-amd64-cpython-310\xformers\sparse
copying xformers\sparse\csr_tensor.py → build\lib.win-amd64-cpython-310\xformers\sparse
copying xformers\sparse\utils.py → build\lib.win-amd64-cpython-310\xformers\sparse
copying xformers\sparse_csr_ops.py → build\lib.win-amd64-cpython-310\xformers\sparse
copying xformers\sparse_init_.py → build\lib.win-amd64-cpython-310\xformers\sparse
creating build\lib.win-amd64-cpython-310\xformers\triton
copying xformers\triton\vararg_kernel.py → build\lib.win-amd64-cpython-310\xformers\triton
copying xformers\triton_init_.py → build\lib.win-amd64-cpython-310\xformers\triton
creating build\lib.win-amd64-cpython-310\xformers_flash_attn
copying xformers_flash_attn\bert_padding.py → build\lib.win-amd64-cpython-310\xformers_flash_attn
copying xformers_flash_attn\flash_attn_interface.py → build\lib.win-amd64-cpython-310\xformers_flash_attn
copying xformers_flash_attn\flash_attn_triton.py → build\lib.win-amd64-cpython-310\xformers_flash_attn
copying xformers_flash_attn\flash_attn_triton_og.py → build\lib.win-amd64-cpython-310\xformers_flash_attn
copying xformers_flash_attn\flash_blocksparse_attention.py → build\lib.win-amd64-cpython-310\xformers_flash_attn
copying xformers_flash_attn\flash_blocksparse_attn_interface.py → build\lib.win-amd64-cpython-310\xformers_flash_attn
copying xformers_flash_attn\fused_softmax.py → build\lib.win-amd64-cpython-310\xformers_flash_attn
copying xformers_flash_attn_init_.py → build\lib.win-amd64-cpython-310\xformers_flash_attn
creating build\lib.win-amd64-cpython-310\xformers\benchmarks\LRA
copying xformers\benchmarks\LRA\batch_fetch_results.py → build\lib.win-amd64-cpython-310\xformers\benchmarks\LRA
copying xformers\benchmarks\LRA\batch_submit.py → build\lib.win-amd64-cpython-310\xformers\benchmarks\LRA
copying xformers\benchmarks\LRA\run_grid_search.py → build\lib.win-amd64-cpython-310\xformers\benchmarks\LRA
copying xformers\benchmarks\LRA\run_tasks.py → build\lib.win-amd64-cpython-310\xformers\benchmarks\LRA
copying xformers\benchmarks\LRA\run_with_submitit.py → build\lib.win-amd64-cpython-310\xformers\benchmarks\LRA
copying xformers\benchmarks\LRA_init_.py → build\lib.win-amd64-cpython-310\xformers\benchmarks\LRA
creating build\lib.win-amd64-cpython-310\xformers\benchmarks\LRA\code
copying xformers\benchmarks\LRA\code\dataset.py → build\lib.win-amd64-cpython-310\xformers\benchmarks\LRA\code
copying xformers\benchmarks\LRA\code\model_wrapper.py → build\lib.win-amd64-cpython-310\xformers\benchmarks\LRA\code
copying xformers\benchmarks\LRA\code_init_.py → build\lib.win-amd64-cpython-310\xformers\benchmarks\LRA\code
creating build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\attention_mask.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\attention_patterns.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\base.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\compositional.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\core.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\favor.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\fourier_mix.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\global_tokens.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\lambda_layer.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\linformer.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\local.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\nystrom.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\ortho.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\pooling.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\random.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\scaled_dot_product.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\sparsity_config.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\utils.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention\visual.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention_sputnik_sparse.py → build\lib.win-amd64-cpython-310\xformers\components\attention
copying xformers\components\attention_init_.py → build\lib.win-amd64-cpython-310\xformers\components\attention
creating build\lib.win-amd64-cpython-310\xformers\components\feedforward
copying xformers\components\feedforward\base.py → build\lib.win-amd64-cpython-310\xformers\components\feedforward
copying xformers\components\feedforward\conv_mlp.py → build\lib.win-amd64-cpython-310\xformers\components\feedforward
copying xformers\components\feedforward\mixture_of_experts.py → build\lib.win-amd64-cpython-310\xformers\components\feedforward
copying xformers\components\feedforward\mlp.py → build\lib.win-amd64-cpython-310\xformers\components\feedforward
copying xformers\components\feedforward_init_.py → build\lib.win-amd64-cpython-310\xformers\components\feedforward
creating build\lib.win-amd64-cpython-310\xformers\components\positional_embedding
copying xformers\components\positional_embedding\base.py → build\lib.win-amd64-cpython-310\xformers\components\positional_embedding
copying xformers\components\positional_embedding\param.py → build\lib.win-amd64-cpython-310\xformers\components\positional_embedding
copying xformers\components\positional_embedding\rotary.py → build\lib.win-amd64-cpython-310\xformers\components\positional_embedding
copying xformers\components\positional_embedding\sine.py → build\lib.win-amd64-cpython-310\xformers\components\positional_embedding
copying xformers\components\positional_embedding\vocab.py → build\lib.win-amd64-cpython-310\xformers\components\positional_embedding
copying xformers\components\positional_embedding_init_.py → build\lib.win-amd64-cpython-310\xformers\components\positional_embedding
creating build\lib.win-amd64-cpython-310\xformers\components\attention\feature_maps
copying xformers\components\attention\feature_maps\base.py → build\lib.win-amd64-cpython-310\xformers\components\attention\feature_maps
copying xformers\components\attention\feature_maps\softmax.py → build\lib.win-amd64-cpython-310\xformers\components\attention\feature_maps
copying xformers\components\attention\feature_maps_init_.py → build\lib.win-amd64-cpython-310\xformers\components\attention\feature_maps
creating build\lib.win-amd64-cpython-310\xformers\ops\fmha
copying xformers\ops\fmha\attn_bias.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha
copying xformers\ops\fmha\ck.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha
copying xformers\ops\fmha\ck_decoder.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha
copying xformers\ops\fmha\ck_splitk.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha
copying xformers\ops\fmha\common.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha
copying xformers\ops\fmha\cutlass.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha
copying xformers\ops\fmha\dispatch.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha
copying xformers\ops\fmha\flash.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha
copying xformers\ops\fmha\flash3.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha
copying xformers\ops\fmha\torch_attention_compat.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha
copying xformers\ops\fmha\triton_splitk.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha
copying xformers\ops\fmha_init_.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha
creating build\lib.win-amd64-cpython-310\xformers\ops_triton
copying xformers\ops_triton\k_index_select_cat.py → build\lib.win-amd64-cpython-310\xformers\ops_triton
copying xformers\ops_triton\k_scaled_index_add.py → build\lib.win-amd64-cpython-310\xformers\ops_triton
copying xformers\ops_triton\rmsnorm_kernels.py → build\lib.win-amd64-cpython-310\xformers\ops_triton
copying xformers\ops_triton\rope_padded_kernels.py → build\lib.win-amd64-cpython-310\xformers\ops_triton
copying xformers\ops_triton\tiled_matmul_kernels.py → build\lib.win-amd64-cpython-310\xformers\ops_triton
copying xformers\ops_triton_init_.py → build\lib.win-amd64-cpython-310\xformers\ops_triton
creating build\lib.win-amd64-cpython-310\xformers\ops\fmha_triton
copying xformers\ops\fmha_triton\splitk_kernels.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha_triton
copying xformers\ops\fmha_triton_init_.py → build\lib.win-amd64-cpython-310\xformers\ops\fmha_triton
creating build\lib.win-amd64-cpython-310\xformers_flash_attn\layers
copying xformers_flash_attn\layers\patch_embed.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\layers
copying xformers_flash_attn\layers\rotary.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\layers
copying xformers_flash_attn\layers_init_.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\layers
creating build\lib.win-amd64-cpython-310\xformers_flash_attn\losses
copying xformers_flash_attn\losses\cross_entropy.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\losses
copying xformers_flash_attn\losses_init_.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\losses
creating build\lib.win-amd64-cpython-310\xformers_flash_attn\models
copying xformers_flash_attn\models\baichuan.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\models
copying xformers_flash_attn\models\bert.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\models
copying xformers_flash_attn\models\bigcode.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\models
copying xformers_flash_attn\models\btlm.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\models
copying xformers_flash_attn\models\falcon.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\models
copying xformers_flash_attn\models\gpt.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\models
copying xformers_flash_attn\models\gptj.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\models
copying xformers_flash_attn\models\gpt_neox.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\models
copying xformers_flash_attn\models\llama.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\models
copying xformers_flash_attn\models\opt.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\models
copying xformers_flash_attn\models\vit.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\models
copying xformers_flash_attn\models_init_.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\models
creating build\lib.win-amd64-cpython-310\xformers_flash_attn\modules
copying xformers_flash_attn\modules\block.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\modules
copying xformers_flash_attn\modules\embedding.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\modules
copying xformers_flash_attn\modules\mha.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\modules
copying xformers_flash_attn\modules\mlp.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\modules
copying xformers_flash_attn\modules_init_.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\modules
creating build\lib.win-amd64-cpython-310\xformers_flash_attn\ops
copying xformers_flash_attn\ops\activations.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\ops
copying xformers_flash_attn\ops\fused_dense.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\ops
copying xformers_flash_attn\ops\layer_norm.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\ops
copying xformers_flash_attn\ops\rms_norm.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\ops
copying xformers_flash_attn\ops_init_.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\ops
creating build\lib.win-amd64-cpython-310\xformers_flash_attn\utils
copying xformers_flash_attn\utils\benchmark.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\utils
copying xformers_flash_attn\utils\distributed.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\utils
copying xformers_flash_attn\utils\generation.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\utils
copying xformers_flash_attn\utils\pretrained.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\utils
copying xformers_flash_attn\utils_init_.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\utils
creating build\lib.win-amd64-cpython-310\xformers_flash_attn\ops\triton
copying xformers_flash_attn\ops\triton\cross_entropy.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\ops\triton
copying xformers_flash_attn\ops\triton\k_activations.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\ops\triton
copying xformers_flash_attn\ops\triton\layer_norm.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\ops\triton
copying xformers_flash_attn\ops\triton\linear.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\ops\triton
copying xformers_flash_attn\ops\triton\mlp.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\ops\triton
copying xformers_flash_attn\ops\triton\rotary.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\ops\triton
copying xformers_flash_attn\ops\triton_init_.py → build\lib.win-amd64-cpython-310\xformers_flash_attn\ops\triton
running build_ext

note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for xformers
Running setup.py clean for xformers
Failed to build xformers
ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (xformers)

Let me know if i have to paste all the lines or if these are enough.

Can’t get trought this, i’m sorry–

1 Like

It seems like it doesn’t help in some environments.
Let’s try software other than mistral_inference.

1 Like

i solved this in a different way. Ty!

1 Like

How did you solve it? I have the same error.