vrr/unsloth
2
0
Fork 0
mirror of https://github.com/unslothai/unsloth.git synced 2026-07-09 15:58:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 29
unsloth/tests
History
Daniel Han cd9d251f15
Fix fast inference crash on compressed-tensors FP8 models (#7025) 
* Fix fast_gemv crash on compressed-tensors FP8 models

Loading a compressed-tensors FP8 checkpoint (for example
unsloth/Llama-3.2-1B-Instruct-FP8-Block) with fast_inference=False and
running a forward crashed with 'Parameter object has no attribute absmax'
inside fast_gemv.

A compressed-tensors CompressedLinear exposes an already dequantized bf16
weight at forward time while keeping a weight_scale Parameter. The quant
state resolution in get_lora_parameters/get_lora_parameters_bias fell back
to that weight_scale, so a bf16 weight was routed into the bitsandbytes
fast_gemv/fast_dequantize path, which expects a bitsandbytes QuantState
with an absmax attribute.

Only fall back to weight_scale_inv/weight_scale when the weight is still
fp8. A decompressed bf16 weight then resolves to no quant state and flows
through the normal bf16 path, which already handles bias and the LoRA
backward. Real fp8 and bitsandbytes 4bit weights are unchanged.

* Skip the fast_gemv dispatch test before importing unsloth when bitsandbytes is absent
2026-07-09 04:10:59 -07:00
..
notebooks Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
python Fix Windows installer torch index override (#6972) 2026-07-09 03:46:47 -07:00
qlora Formatting: ruff line-length 100, kwarg-spacing passes, drop blank after short local imports (#6079) 2026-06-08 04:24:13 -07:00
saving Fix repeated base model downloads across checkpoint exports (#6896) 2026-07-06 23:38:29 -07:00
security scan_packages: key baseline on matched-code hash so payloads in baselined files are not auto-suppressed (#6552) 2026-07-01 04:03:59 -07:00
sh Fix Windows installer torch index override (#6972) 2026-07-09 03:46:47 -07:00
studio Retry the Studio UI shutdown re-login on transient goto timeout (#7027) 2026-07-09 01:46:14 -07:00
studio_setup_ps1 Make Visual Studio + CMake optional on Windows (prebuilt llama.cpp needs no build tools) (#6499) 2026-06-22 01:11:09 -07:00
utils Guard RoPE scaling against the transformers v5 buffer blank; honor extended RoPE factor (#6925) 2026-07-07 04:16:57 -07:00
version_compat Fix FastSentenceTransformer Qwen embedding preprocessing (#6939) 2026-07-09 01:46:22 -07:00
vllm_compat Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
__init__.py Qwen 3, Bug Fixes (#2445) 2025-04-30 22:38:39 -07:00
_zoo_aggressive_cuda_spoof.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
_zoo_rocm_spoof.py Add RDNA 2/3/4 ROCm routing tests via a CPU-only torch spoof (#6935) 2026-07-07 04:41:37 -07:00
conftest.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
run_all.sh Installer: make UV_OVERRIDE space-safe on Apple Silicon (#6503) (#6639) 2026-06-24 17:34:18 -07:00
test_attention_implementation.py fix(gpt-oss): prefer flex attention over sdpa (#5701) 2026-05-22 08:38:38 -07:00
test_attn_impl_honor_explicit.py Honor an explicit sdpa or flex_attention request when flash is disabled (#6847) 2026-07-06 05:45:45 -07:00
test_bad_mappings_redirect.py Fix BAD_MAPPINGS not redirecting the -unsloth-bnb-4bit dynamic quants (#6949) 2026-07-08 17:37:44 -03:00
test_callback_signature_drift.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
test_cli_export_unpacking.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
test_enforce_kwargs_spacing.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
test_fast_gemv_dispatch.py Fix fast inference crash on compressed-tensors FP8 models (#7025) 2026-07-09 04:10:59 -07:00
test_fast_generate_slow_guard.py fast_generate: clear error for vLLM-style inputs when fast_inference=False (#6786) 2026-07-03 08:16:32 -07:00
test_finetune_last_n_layers.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
test_fp8_device_context.py Guard FP8 Triton launches with tensor device context (#6888) 2026-07-08 18:32:51 -03:00
test_fp8_tiny_e8m0.py Handle odd shapes and non-float scales in FP8BlockQuantLinear (#6848) 2026-07-06 05:44:55 -07:00
test_fused_ce_not_return_dict_logits.py fix: use EMPTY_LOGITS on the fused-CE not-return_dict path (#2068) (#6482) 2026-06-23 01:26:55 -07:00
test_gemma4_chat_template.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
test_gemma_2b_mapper_key.py Fix duplicate unsloth/gemma-2b-bnb-4bit mapper key routing the base 4bit repo to the instruct model (#6891) 2026-07-08 17:40:39 -03:00
test_generate_kwarg_gate.py Fix gpt-oss offload_embedding and generate() kwargs, and guard offload_embedding on tied/vLLM models (#6774) 2026-07-01 22:39:00 -07:00
test_get_model_name.py Formatting: ruff line-length 100, kwarg-spacing passes, drop blank after short local imports (#6079) 2026-06-08 04:24:13 -07:00
test_gradient_checkpointing_restore.py Fix TrainingArguments silently disabling unsloth gradient checkpointing (#6829) 2026-07-03 16:35:02 +01:00
test_ignored_tokenizer_casing.py Match IGNORED_TOKENIZER_NAMES case-insensitively (#6620) 2026-06-23 19:40:50 -03:00
test_import_fixes_drift.py fix: keep LoRA reloads working with PEFT 0.19 (#6748) 2026-06-30 20:26:57 +01:00
test_loader_glob_skip.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
test_missing_torchvision_vlm.py Fix misleading 'only for image models' error for Qwen3-VL when torchvision is missing (#6525) 2026-06-23 01:28:09 -07:00
test_model_registry.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
test_moe_lora_targets.py Scope MoE expert LoRA detection to actual MLP projection targets (#6849) 2026-07-06 05:45:06 -07:00
test_multi_image_grpo_chunking.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
test_nvfp4_quant_load.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
test_offline_loading_helpers.py Fix offline checkpoint load/export: "tokenizer is weirdly not loaded" (#6554) 2026-06-25 23:16:53 -07:00
test_offload_embedding_hooks.py Fix gpt-oss offload_embedding and generate() kwargs, and guard offload_embedding on tied/vLLM models (#6774) 2026-07-01 22:39:00 -07:00
test_offload_tied_guard.py Fix gpt-oss offload_embedding and generate() kwargs, and guard offload_embedding on tied/vLLM models (#6774) 2026-07-01 22:39:00 -07:00
test_peft_tensor_parallel_compat.py fix: keep LoRA reloads working with PEFT 0.19 (#6748) 2026-06-30 20:26:57 +01:00
test_peft_weight_converter_compat.py Formatting: ruff line-length 100, kwarg-spacing passes, drop blank after short local imports (#6079) 2026-06-08 04:24:13 -07:00
test_prefetch_snapshot_scope.py Auto Xet to HTTP download fallback in from_pretrained; share Studio's fallback via unsloth_zoo (#6638) 2026-07-06 05:13:25 -07:00
test_pretrain_compile_reset.py Add regression tests for the stray-forward compile-cache reset (#6569) 2026-06-22 07:22:47 -07:00
test_public_api_surface.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
test_raw_text.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
test_resolve_model_class.py Formatting: ruff line-length 100, kwarg-spacing passes, drop blank after short local imports (#6079) 2026-06-08 04:24:13 -07:00
test_studio_install_workspace_guard.py Update studio root-resilience tests for the inference-backend refactor (#6490) (#6553) 2026-06-22 01:10:49 -07:00
test_studio_root_resilience.py Update studio root-resilience tests for the inference-backend refactor (#6490) (#6553) 2026-06-22 01:10:49 -07:00
test_studio_shutdown_thread_wait.py Studio: fix Ctrl+C shutdown ordering (installer shell + uvicorn thread wait) (#6566) 2026-06-22 07:41:10 -07:00
test_synthetic_chunk_data.py fix: correct class name in SyntheticDataKit.chunk_data guard message (#6901) 2026-07-06 07:11:57 -07:00
test_tool_mask_zoo_compat.py Formatting: ruff line-length 100, kwarg-spacing passes, drop blank after short local imports (#6079) 2026-06-08 04:24:13 -07:00
test_uninitialized_position_ids.py Load DeepSeek-OCR and other VLMs that register AutoModel in auto_map (#6421) 2026-06-18 07:03:43 -07:00
test_video_path_validation.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00
test_vllm_broken_detection.py Fix fast_inference crash on ABI-broken vLLM: probe compiled extensions, not just import vllm (#6621) 2026-06-26 22:43:36 -07:00
test_windows_rocm_bnb_version.py Reduce and tighten comments and docstrings across the test suite (#6429) 2026-06-18 01:07:09 -07:00