GitLab

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: Cody Yu <hao.yu.cody@gmail.com>

Co-authored-by: Elisei Smirnov <el.smirnov@innopolis.university>

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).

Allow dummy load format for fp8,
torch.uniform_ doesn't support FP8 at the moment
Co-authored-by: Mor Zusman <morz@ai21.com>

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: Robert Shaw <rshaw@neuralmagic.com>

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

[Core][2/N] Model runner refactoring part 2. Combine prepare prefill / decode to a single API (#4681)

This PR combines prepare_prompt and prepare_decode into a single API. This PR also coelsce the attn metadata for prefill/decode to a single class and allow to slice them when running attn backend.

It also refactors subquery_start_loc which was not refactored in the previous PR

[Frontend] [Core] perf: Automatically detect vLLM-tensorized model, update `tensorizer` to version 2.9.0 (#4208)

Storing exception frame is extremely prone to circular refernece because it contains the reference to objects.

When tensorizer is not installed, it leaks llm instance because error frame has references to various modules which cause circular reference problem.

I also found spec decoding has a circular reference issue, and I solved it using weakref.proxy.

This PR improves the FP8 performance of linear layers, which had been lacking before (#4118 (comment) and #4118 (comment)).

We noticed that CUBLASLt can find a better algorithm if the first dimension of the matrix is greater than 16. So this PR enlarges matrices appropriately during quantization. This improves FP8 performance and removes the performance regression vs. FP16, in many cases exceeding FP16 performance.

Here are benchmarks on llama3 70b (ITL numbers for 1000 input and 50 output tokens at fixed qps and at TP 4), all FP8 measurements are for dynamic quantization:

qps = 1: 24 ms (FP8, this PR), 32 ms (FP8, previous main), 26 ms (FP16)
qps = 2: 26 ms (FP8, this PR), 34ms (FP8, previous main), 28 ms (FP16) 
qps = 4: 33 ms (FP8, this PR), 44 ms (FP8, previous main), 36 ms (FP16)
qps = 6: 46 ms (FP8, this PR), 56 ms (FP8, previous main), 54 ms (FP16)
qps = 8: 85 ms (FP8, this PR), 85 ms (FP8, previous main), 138 ms (FP16)

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>

Co-authored-by: Cade Daniel <edacih@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.