* Add the mmv kernels for smaller sizes.
* Support more mmv kernels.
* Use the new kernels.
* Fix the call.
* Silly fix.
* Improve the testing.
* Fix for dmmv.
* Add another dedicated test for the batching mmv.
* Fix for the batch dim in the quantized matmul example.
* Enable more tests on cuda.
* Add a test for qmm with a batch.
* Fix the zeros-dim test on metal.
* Hook the quantized matmul cuda kernels.
* Add a (currently broken) test.
* Kernel fixes.
* Fix by transposing the rhs matrix.
* Add the q4-1 kernels.
* Proper block sizes.
* More details in the tests.
* Add more cuda kernels for quantized matmul.
* Add the vec-dot bits.
* Expose the quantized matmul-vec kernels.
* Also include the quantize-q8-1 kernel.
* Glue code for the q8-1 quantization.
* mm-vec product via q8-1 quantization.
* Add a test.
* Add a mm test.
* Get the test to return some sensible results.
* Also test dmmv.
* Fix the launch params.
* Allow for tweaking the force_dmmv parameter while it's experimental.
* Improve metal buffer usage
* Clone cpu storage when loading to reduce wait_until_complete calls
* Use powers of two for buffer sizes so reuse is more likely.
* Select best available buffer by size.
* Add count to MetalStorage -> can use buffer with different size
Co-authored-by: Chris Fleetwood <christopher.fleetwood@huggingface.co>
* Simplify new buffer creation without blit copy. Revert &[] -> Vec
* Add documentation on newBufferWithBytes safety / synchronization
* Drop unused buffers after command buffer is done syncing.
---------
Co-authored-by: Chris Fleetwood <christopher.fleetwood@huggingface.co>
* Boilerplate for the quantized cuda support.
* More basic cuda support.
* More cuda quantization (quantize on cpu for now).
* Add the dequantization bit.
* Start adding some dedicated cuda kernels from llama.cpp.
* Move the kernel code.
* Start interfacing with the kernel.
* Tweak the kernel launch params.
* Bugfix for quantized metal.
* Fix some clippy lints.
* Tweak the launch parameters.
* Tweak cuda basics to perform a quantized matmul.
* Perform the dequantization on the cpu + use cublas for matmul.
* Add the dequantization kernel.
* Test the qmatmul.
* More kernels.
* Matmul-vec kernel.
* Add a couple kernels.
* More dequantization kernels.
* Metal quantized modifications proposal.
- Add a device param, wherever needed.
- Create new QMetal storage thing that implements QuantizedType.
- Update everywhere needed.
Fix Python.
Fixing examples.
Fix: fmt + clippy + stub.
Moving everything around.
Only missing the actual implems.
Fixing everything + adding dequantized kernels.
More work.
Fixing matmul.
Fmt + Clippy
Some clippy fixes.
Working state.
Q2K Metal -> Bugged (also present in GGML).
Q4K CPU -> Bugged (present previously, new test catch it).
Q5K CPU -> Bugged (present previously).
Q8_1 Both -> Never really implemented it seems
Q8K metal -> Never implemented in metal
Fixing Q2K bug (present in ggml).
* Cleanup.
* Fix the rebase.
* Removing the fences speeds everything up and *is* correct this time...
* Cleanup the fence.
* After rebase.
* Bad code removal.
* Rebase after phi2 merge + fix replit default to CPU.
* Making the CI happy.
* More happy tests.
---------
Co-authored-by: Nicolas Patry <nicolas@Nicolass-MacBook-Pro.local>
* Simpler repro for the neon optimization issue.
* Bugfix for q4k.
* Improve the fix, share the dot-prod bit.
* Clippy fixes.
* Fix for q6k.
* Also fix for q2k.
* Use the new shared dotprod.
* Add more testing.
* Add more pyo3 support.
* Add some support for quantized tensors in pyo3.
* Add an arc layer on qmatmul.
* Add the quantized matmul.
* Quantization support.
* More quantization support.
* Test the python quantization.
