* Add the cuda dequantize f16 kernels.
* Expose the cuda kernels.
* Add some testing + fix.
* Test the other cases too.
* A few more tests.
* Add an environment variable to enable the dequantize f16 + matmul behavior.
* 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.
* 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.
* first q2 implementation
* First Q4K and Q5K implementations
* fix `q2k` and `q5k`
* Some first cleanups
* run `clippy` on tests
* finally implement `q3k`
* deactivate `q3k` test on macos
* also disable the test on linux
* Fix floating bits in `q3k` dequantization
* Refactoring pass + reorder quants in file
* `fmt`
* Re-add `src` asserts and redefine `dst`
* Print the detected arch options.
* Add the q6k quantization.
* Add a currently broken test.
* Bugfix.
* Bugfix.
* Another bugfix.
* Another bugfix + get the test to work.
* Add more stats to the ggml example.
* Build a quantized model from the file content.
* Move the tensor retrieval in the main crate.
* Start adding the forward pass.
* Add more to the forward pass of the quantized llama.
* Apply the attention layers.
* Add the sampling loop.
* Get the sampling loop to work.
* Minor tweak.
* Add a quantize/dequantize test.
* Bugfix.
* Add a comment + swap the order.
* Bugfixes.
