Dipika Sikka

[Timings] Add the ability to log times for async and sync calls

1

# Summary - Add the ability to time function calls - Will be enabled unless the `--disable-log-stats` cli arg is used for the server as the timer's init and average...

[Kernel] Initial Activation Quantization Support

3

# Summary - Initial support for Activation Quantization (specifically static-per tensor for W8A8) - Adds `CompressedTensorsConfig` and `CompressedTensorsLinearMethod` to support models quantized through [sparseml](https://github.com/neuralmagic/sparseml) and saved through [compressed-tensors](https://github.com/neuralmagic/compressed-tensors) - Adds...

- Blocked on k8 runners being available. Only aws runners currently work

# Summary - Add a step to publish the nightly wheel using the nm-action: https://github.com/neuralmagic/nm-actions/blob/main/actions/publish-whl/action.yml - Once built, updated to add in a step to build the nightly container using...

# Summary - Add a `CompressedTensorsW8A8DynamicToken` scheme to support dynamic-per token activation quantization - Update config parsing to support updates made to the `config.json` / quantization config provided with the...

[Misc] Update `gptq_marlin` to use new vLLMParameters

2

# Summary - Updates the `gptq_marlin` parameters to use `vLLMParameters` to simplify linear layer weight loading - Updates to add `PackedColumnParameter` to support packed parameters without row parallelism

[Misc] Update Fused MoE weight loading

2

# Summary: - Splits up #6422 into two separate PRs. This is the first of the two. The second will leverage the weight loading changes introduced in this PR while...

add awq fused moe method

1

FILL IN THE PR DESCRIPTION HERE FIX #xxxx (*link existing issues this PR will resolve*) **BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE** --- PR...