11 Pull requests merged by 9 people

• Add float8 MoE training readme and runnable example

  #2353 merged Jun 11, 2025

• float8 moe training conversion API prototype

  #2275 merged Jun 10, 2025

• Add static quant tutorial

  #2047 merged Jun 10, 2025

• Update QAT docs, highlight axolotl integration

  #2266 merged Jun 10, 2025

• [BE] Rename qparams for tinygemm

  #2344 merged Jun 10, 2025

• Add support for bmm and to for fbgemm Tensor

  #2337 merged Jun 10, 2025

• add cast config for fp8 enablement

  #2328 merged Jun 10, 2025

• Fix Per Tensor 3d rehsape

  #2293 merged Jun 9, 2025

• Update Quantization docs to show newer AOConfigs

  #2317 merged Jun 9, 2025

• Enhance test_autoquant_compile to support ROCm

  #2100 merged Jun 9, 2025

• Migrate xnnpack/vulkan/boltnn pt2e from torch.ao to torchao (#11363)

  #2302 merged Jun 9, 2025

6 Pull requests opened by 5 people

• Replace debug handle with `from_node` to trace operator transformation

  #2339 opened Jun 9, 2025

• Inference tutorial - Part 3 of e2e series [WIP]

  #2343 opened Jun 9, 2025

• Add inplace quantizer examples

  #2345 opened Jun 10, 2025

• Add Tutorial on E2E integration into VLLM and minimal Subclass

  #2346 opened Jun 10, 2025

• [BE] Convert quant_primitives methods private

  #2350 opened Jun 10, 2025

• [float8] Add fnuz fp8 dtypes to Float8Layout

  #2351 opened Jun 10, 2025

4 Issues opened by 4 people

• Support `torch.int4` `target_dtype` for ops `choose_qparams_affine`, `quantize_affine`, `dequantize_affine`

  #2354 opened Jun 10, 2025

• DISABLED test_int4_weight_only_quant_subclass_grouped_5_cuda (__main__.TestSubclass)

  #2352 opened Jun 10, 2025

• Add _apply_fn_to_data in AOBaseClass

  #2349 opened Jun 10, 2025

• Distributing ao tensor subclasses in .safetensors checkpoints

  #2338 opened Jun 9, 2025

15 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• DUMMY PR: add support for hpu in float8 base and compile test for torch ao

  #2326 commented on Jun 10, 2025 • 14 new comments

• moe quant with dedicated kernels [wip]

  #2325 commented on Jun 9, 2025 • 3 new comments

• ROCm mx-fp8 Gemm

  #2066 commented on Jun 10, 2025 • 2 new comments

• skip quant/dequant decomposed

  #2299 commented on Jun 10, 2025 • 1 new comment

• Add round_scales_to_power_of_2 option for float quantization

  #2323 commented on Jun 9, 2025 • 1 new comment

• BF16 stochastic rounding does not work distributed (FSDP)

  #2296 commented on Jun 8, 2025 • 0 new comments

• [Question] Combining QAT and Sparsity Training

  #2310 commented on Jun 9, 2025 • 0 new comments

• [Windows][build]two Build failure on Windows on latest main branch

  #2297 commented on Jun 9, 2025 • 0 new comments

• int4_weight_only get plain weight are padded

  #2249 commented on Jun 11, 2025 • 0 new comments

• [CPU] Enable DA8W4 on CPU

  #2128 commented on Jun 8, 2025 • 0 new comments

• Eval hf models using lm_eval

  #2179 commented on Jun 9, 2025 • 0 new comments

• [WIP] Enable Int4WeightOnlyGPTQQuantizer on Intel GPU.

  #2200 commented on Jun 10, 2025 • 0 new comments

• Fix failing tests on h100

  #2231 commented on Jun 9, 2025 • 0 new comments

• Build mxfp4 kernel for sm120a

  #2285 commented on Jun 8, 2025 • 0 new comments

• [BE] Make ScalingGranularity module level so it can be rendered in API ref on docsite

  #2314 commented on Jun 9, 2025 • 0 new comments