GitLab

Co-authored-by: Roger Wang <ywang@roblox.com>

Co-authored-by: team <calvinn.ng@ahrefs.com>

Co-authored-by: rsnm2 <rshaw@neuralmagic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>

Co-authored-by: beagleski <yunanzhang@microsoft.com>
Co-authored-by: bapatra <bapatra@microsoft.com>
Co-authored-by: Barun Patra <codedecde@users.noreply.github.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>

Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>

The 2nd PR for #4532.

This PR supports loading FP8 kv-cache scaling factors from a FP8 checkpoint (with .kv_scale parameter).

Currently we need to call rotary embedding kernel for each LoRA, which makes it hard to serve multiple long context length LoRA. Add batched rotary embedding kernel and pipe it through.

It replaces the rotary embedding layer to the one that is aware of multiple cos-sin-cache per scaling factors.

Follow up of https://github.com/vllm-project/vllm/pull/3095/files

Co-authored-by: Dash Desai <1723932+iamontheinet@users.noreply.github.com>
Co-authored-by: Aurick Qiao <qiao@aurick.net>
Co-authored-by: Aurick Qiao <aurick.qiao@snowflake.com>
Co-authored-by: Aurick Qiao <aurickq@users.noreply.github.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>

[Kernel] Support MoE Fp8 Checkpoints for Mixtral (Static Weights with Dynamic/Static Activations) (#4527)

Follow on to #4332 to enable FP8 checkpoint loading for Mixtral and supersedes #4436.

This PR enables the following checkpoint loading features for Mixtral:

Supports loading fp8 checkpoints for Mixtral, such as this "nm-testing/Mixtral-8x7B-Instruct-v0.1-FP8" test model
Supports static or dynamic activation quantization with static weight quantization (all per tensor)
Supports different scales for each expert weight
Supports Fp8 in QKV layer
Notes:

The Expert Gate/Router always runs at half / full precision for now.
If there are different weight scales between QKV layer (for separate QKV weights), they are re-quantized using layer.weight_scale.max() so we can have a single gemm for performance.

Remove the device="cuda" declarations in mixtral as promised in #4343

Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>