chore(deps): update dependency compressed-tensors to v0.15.0.1

[renovate]

This PR contains the following updates:

Package	Change	Age	Confidence
compressed-tensors	==0.13.0 → ==0.15.0.1

---

Release Notes

vllm-project/compressed-tensors (compressed-tensors)

v0.15.0.1: Compressed-Tensors v0.15.0.1

Compare Source

What's Changed

• Remove upper limit on torch version in setup.py by @​dsikka in #​674

Full Changelog: vllm-project/compressed-tensors@0.15.0...0.15.0.1

v0.15.0: Compressed-Tensors v0.15.0

Compare Source

What's Changed

• [Bugfix] Support N-dimensional tensors in pack_to_int32 and unpack_from_int32 by @​Yatimai in #​609
• [Entrypoints] Convert Checkpoint by @​brian-dellabetta in #​607
• pr to trigger re-build by @​brian-dellabetta in #​619
• [BugFix] dispatch_model failing with MemoryError on CPU-only environments by @​EdalatiAli in #​620
• [Bugfix] [Refactor] Simplify linear forward, fix offloaded generation runtime by @​kylesayrs in #​614
• [Bugfix] Fix linter for dispatch function by @​kylesayrs in #​613
• [Bugfix] Fix distributed disk update_offload by @​kylesayrs in #​617
• [Bugfix] [Offload] Make sure disk operations only happen on rank 0 by @​kylesayrs in #​626
• [Offload] Require offload_folder when performing disk offloading by @​kylesayrs in #​602
• fix: use float base in pow to avoid Inductor dtype mismatch by @​Bias92 in #​627
• Fix cross-device CUDA offloading in DeviceCache, offload_module, and offload_model by @​changjonathanc in #​621
• [Agent] Add style and test claude skills by @​kylesayrs in #​616
• [Compressors] Refactor compressors, remove sparsity & CompressedLinear by @​kylesayrs in #​610
• Fix race condition in distributed disk tests by @​kylesayrs in #​635
• [Offload] Allow nested offload disable contexts by @​kylesayrs in #​632
• [Perf] Fuse quantize+dequantize into single pass for fake_quantize by @​Etelis in #​636
• Update generate_gparam calculation to handle NaNs and Infs by @​dsikka in #​637
• [Docs] Offloading documentation by @​kylesayrs in #​612
• [Offload] Better performance for update_offload_parameter by @​kylesayrs in #​633
• Add MXFP8 Support by @​yiliu30 in #​630
• [Bugfix] FP4 Checkpoint Backwards Compatibility by @​kylesayrs in #​644
• Update torch version constraint in setup.py by @​dsikka in #​649
• [MTP] Add functionality to save mtp layers from the original model + refactor safetensors utilities by @​dsikka in #​640
• [Refactor] Rename offload_model to set_onload_device by @​nrmlthms in #​643
• Rounding out offload utils + bugfix by @​HDCharles in #​650
• [bugfix][kv_cache_scheme] update KV_CACHE_TARGETS and use it by @​brian-dellabetta in #​653
• fix activation ordering documentation by @​HDCharles in #​654
• [Refactor] Split _process_quantization into per-strategy functions by @​Etelis in #​639
• Add transformers v5 support and LAPACK GPU fallback by @​AndreasKaratzas in #​661
• Update transformers and remove the upper bound by @​dhuangnm in #​663

New Contributors

• @​Yatimai made their first contribution in #​609
• @​EdalatiAli made their first contribution in #​620
• @​Bias92 made their first contribution in #​627
• @​changjonathanc made their first contribution in #​621
• @​yiliu30 made their first contribution in #​630
• @​nrmlthms made their first contribution in #​643
• @​AndreasKaratzas made their first contribution in #​661

Full Changelog: vllm-project/compressed-tensors@0.14.0.1...0.15.0

v0.14.0.1: Compressed Tensors v0.14.0.1

Compare Source

What's Changed

• Patch release to add support for distributed disk cache and fix bugs related to file writing. For more information see #​617

Full Changelog: vllm-project/compressed-tensors@0.14.0...0.14.0.1

v0.14.0: Compressed Tensors v0.14.0

Compare Source

What's Changed

• [decompression] Added qparam decompression by @​shanjiaz in #​537
• Use standard E8M0 scale format for MXFP4 by @​mgoin in #​538
• Add W4AFP8 preset scheme by @​Etelis in #​542
• [MXFP4] Fix scale offset by @​dsikka in #​541
• [CI] Add mergify and stale PR rules by @​dsikka in #​543
• [Offload] Fix delete_offload_parameter, add clear_quantization by @​kylesayrs in #​539
• [Deprecation] Add deprecation warning for marlin24 format by @​Etelis in #​544
• [Offload] Add offloading logic by @​kylesayrs in #​529
• Pin torch by @​dsikka in #​546
• [Testing] Pin transformers by @​kylesayrs in #​549
• limit transformers to <5.0.0 by @​dhuangnm in #​550
• Modernize python310 type hints in quantization forward by @​LudovicoYIN in #​548
• [Offload] Remove Accelerate by @​kylesayrs in #​530
• KV Cache Quantization support deepseek v3 by @​zkl-ai in #​533
• [Bugfix] Remove assert when dispatched to device by @​kylesayrs in #​554
• Modernize python310 type hints in quantization by @​LudovicoYIN in #​553
• [Observers] Change default weight observer to "memoryless_minmax" by @​kylesayrs in #​540
• Update pytest command to include report options by @​dsikka in #​557
• Change runner from IBM to GCP for Python tests by @​dsikka in #​561
• Modernize python310 type hints in utils by @​LudovicoYIN in #​560
• Update quantization strategy validation for actorder by @​dsikka in #​556
• [Offload] DistributedCPUCache by @​kylesayrs in #​534
• [MXFP4][GPTQ] Extend rounding to support FP32 by @​dsikka in #​551
• [Tests] Fix typo, prepare for meta offload tensors by @​kylesayrs in #​562
• Modernize python310 type hints in compressors by @​LudovicoYIN in #​563
• Modernize python310 type hints in transform/offload/registry by @​LudovicoYIN in #​565
• [Offload] [Bugfix] Fix distributed cpu tensor reconstruction by @​kylesayrs in #​567
• [Offload] [Bugfix] Reserve extra dispatch memory for fragmentation by @​kylesayrs in #​566
• Remove Neural Magic copyright by @​Etelis in #​559
• [Transforms] Support loading transforms in transformers by @​kylesayrs in #​528
• [Offload] DistributedDeviceCache by @​kylesayrs in #​568
• Revert "[Transforms] Support loading transforms in transformers" by @​HDCharles in #​578
• [Offload] DiskCache, DistributedDiskCache by @​kylesayrs in #​535
• [Offload] Make update_offload_parameter more async and direct (2) by @​kylesayrs in #​576
• [Copyright] Add vLLM copyright enforcement by @​kylesayrs in #​575
• [Bugfix] Handle updating tensors with gradients by @​kylesayrs in #​580
• [bugfix] get_device_memory rank>0 fix by @​HDCharles in #​582
• Remove upper limit for torch dependency to support 2.10 by @​dsikka in #​583
• Set seed to fix flaky test by @​dsikka in #​584
• [Offload] Convert accelerate for loading/saving by @​kylesayrs in #​572
• [Bugfix] Allow parameter overwrite if shapes do not match by @​kylesayrs in #​586
• [Bugfix] [Offloading] Even more reserved memory, scaling with model size by @​kylesayrs in #​587
• Implement init_dist for distributed setup by @​HDCharles in #​589
• FP8 Block Quantization: Non-Divisible Shape Support by @​Etelis in #​547
• [Bugfix]: Reduce memory usage when load device does not match dispatch device by @​kylesayrs in #​592
• [bugfix] load_offloaded_model qwen3vl8b by @​HDCharles in #​591
• [Offload] clean up deprecation warnings, which can accumulate to 100k+ warnings by @​brian-dellabetta in #​593
• [Offload] Deprecate update_parameter_data by @​kylesayrs in #​588
• [Bugfix] Fix clear_quantization by @​kylesayrs in #​596
• Allow broadcasting fp8 by @​HDCharles in #​603
• fix ruff for release by @​HDCharles in #​604
• [Offload] Fully invertible conversion functions by @​kylesayrs in #​601
• [Offload] Better device/cpu memory estimates when loading with load_offloaded_model by @​kylesayrs in #​605

New Contributors

• @​LudovicoYIN made their first contribution in #​548

Full Changelog: vllm-project/compressed-tensors@0.13.0...0.14.0

---

Configuration

📅 Schedule: (UTC)

• Branch creation
  • At any time (no schedule defined)
• Automerge
  • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR is behind base branch, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

---

• If you want to rebase/retry this PR, check this box

---

This PR was generated by Mend Renovate. View the repository job log.