24 Pull requests merged by 15 people

• 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

• Fix Windows Build

  #2333 merged Jun 7, 2025

• Add slicing support for fbgemm fp8 and int4

  #2308 merged Jun 6, 2025

• Rename kleidi_ai in PackedWeightsType and update references

  #2318 merged Jun 6, 2025

• [BE/docs] Add fp8 rowwise perf table to float8 training readme

  #2312 merged Jun 6, 2025

• Fix broken circular dep error

  #2320 merged Jun 6, 2025

• [BE] [docs] Add float8 pretraining tutorial to docsite

  #2304 merged Jun 5, 2025

• Add Float8ActInt4WeightQATQuantizer

  #2289 merged Jun 5, 2025

• Enable doc build to run on PRs

  #2315 merged Jun 5, 2025

• Fix slicing and get_plain() in GemLite

  #2288 merged Jun 5, 2025

• [BE/docs] Add float8 training api ref to docsite

  #2313 merged Jun 5, 2025

• primitive scale fix

  #2210 merged Jun 5, 2025

• Add support for fbgemm fp8 kernels

  #2276 merged Jun 5, 2025

• Skip native modules if USE_CPP = 0

  #2301 merged Jun 5, 2025

• [sparse] marlin fixes

  #2305 merged Jun 4, 2025

• update float8 training readme to include time measurement

  #2291 merged Jun 4, 2025

• [optim] Fix bug when default dtype is BF16

  #2286 merged Jun 4, 2025

• Define torchao op library by srcs instead of object libraries

  #2290 merged Jun 3, 2025

• Remove valpacking code and associated tests

  #2295 merged Jun 3, 2025

• Fix QAT range learning, ensure scales get gradients

  #2280 merged Jun 3, 2025

• Removing DocBlock to unblock MXFP4 w/ Unwrap Tensor

  #2292 merged Jun 3, 2025

22 Pull requests opened by 15 people

• make bfs_graph_trace as internal function

  #2294 opened Jun 3, 2025

• skip quant/dequant decomposed

  #2299 opened Jun 4, 2025

• In the folder fbcode/pytorch/ao/torchao/ document the following symbol paths:

  #2300 opened Jun 4, 2025

• [Benchmarks] Remove additional baseline calculation

  #2303 opened Jun 4, 2025

• Adding 64x8 Triton kernel

  #2307 opened Jun 4, 2025

• Back out "Add back AOPerModuleConfig for BC (#2282)"

  #2309 opened Jun 5, 2025

• Add Claude MD file

  #2311 opened Jun 5, 2025

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

  #2314 opened Jun 5, 2025

• [BE] Make internal torchao.float8 functions private

  #2321 opened Jun 5, 2025

• add recipe config in aps for fp8

  #2322 opened Jun 5, 2025

• Add round_scales_to_power_of_2 option for float quantization

  #2323 opened Jun 6, 2025

• turn off building tests with cpuinfo

  #2324 opened Jun 6, 2025

• moe quant with dedicated kernels [wip]

  #2325 opened Jun 6, 2025

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

  #2326 opened Jun 6, 2025

• Add dynamic quantization support to gemlite layout

  #2327 opened Jun 6, 2025

• add cast config for fp8 enablement

  #2328 opened Jun 6, 2025

• Add support for bmm and `to` for fbgemm Tensor

  #2337 opened Jun 8, 2025

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

  #2339 opened Jun 9, 2025

• Implemented a new test case for LUT quantization

  #2342 opened Jun 9, 2025

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

  #2343 opened Jun 9, 2025

• [BE] Rename qparams for tinygemm

  #2344 opened Jun 9, 2025

• Add inplace quantizer examples

  #2345 opened Jun 10, 2025

1 Issue closed by 1 person

• convert_to_float8_training and torch.compile make model slow

  #2262 closed Jun 4, 2025

6 Issues opened by 6 people

• Distributing ao tensor subclasses in .safetensors checkpoints

  #2338 opened Jun 9, 2025

• [Question] Combining QAT and Sparsity Training

  #2310 opened Jun 5, 2025

• [FP8 optimizer feature request] Better FP8 Optimizer with Dynamic Range Expansion

  #2306 opened Jun 4, 2025

• Use Int8WeightOnlyConfig to quant wan2.1 model, and export to onnx file, Why the onnx weights in my disk are fp32 precision?

  #2298 opened Jun 4, 2025

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

  #2297 opened Jun 4, 2025

• BF16 stochastic rounding does not work distributed (FSDP)

  #2296 opened Jun 4, 2025

10 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.

• [CPU] Enable DA8W4 on CPU

  #2128 commented on Jun 8, 2025 • 6 new comments

• float8 moe training conversion API prototype

  #2275 commented on Jun 10, 2025 • 4 new comments

• ROCm mx-fp8 Gemm

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

• Add benchmark numbers to dashboard

  #2260 commented on Jun 5, 2025 • 1 new comment

• Tensor Subclass + VLLM Compile

  #2239 commented on Jun 3, 2025 • 0 new comments

• QAT range learning tracker

  #2271 commented on Jun 6, 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 9, 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