GitLab

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

This PR updates the tuning script for the fused_moe kernel to support FP8 and also adds configurations for TP4. Note that for the configuration I removed num_warps and num_stages for small batch sizes since that improved performance and brought the benchmarks on par with the numbers before in that regime to make sure this is a strict improvement over the status quo.

All the numbers below are for mistralai/Mixtral-8x7B-Instruct-v0.1, 1000 input and 50 output tokens.

Before this PR (with static activation scaling):

qps = 1: 9.8 ms ITL, 0.49s e2e latency
qps = 2: 9.7 ms ITL, 0.49s e2e latency 
qps = 4: 10.1 ms ITL, 0.52s e2e latency
qps = 6: 11.9 ms ITL, 0.59s e2e latency
qps = 8: 14.0 ms ITL, 0.70s e2e latency
qps = 10: 15.7 ms ITL, 0.79s e2e latency

After this PR (with static activation scaling):

qps = 1: 9.8 ms ITL, 0.49s e2e latency
qps = 2: 9.7 ms ITL, 0.49s e2e latency
qps = 4: 10.2 ms ITL, 0.53s e2e latency
qps = 6: 11.9 ms ITL, 0.59s e2e latency
qps = 8: 11.9 ms ITL, 0.59s e2e latency
qps = 10: 12.1 ms ITL, 0.61s e2e latency

Co-authored-by: Philipp Moritz <pcmoritz@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>

Co-authored-by: alexm <alexm@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>

Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
Co-authored-by: Travis Johnson <tjohnson31415@gmail.com>

Co-authored-by: DefTruth <31974251+deftruth@users.noreply.github.com>

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

Co-authored-by: Danny Guinther <dguinther@neuralmagic.com>

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

Fixes fp8 iterface which broke in AQLM merge.

This PR is the first step towards fixing https://github.com/vllm-project/vllm/pull/3208

It implements dynamic per-tensor scaling (see https://github.com/vllm-project/vllm/pull/4118), so users do not need to compute activation scales on a calibration dataset and they also don't need to convert their model checkpoints. It is enough to specify the `quantization="fp8"` argument. You can try out the PR like this:

```python
from vllm import LLM, SamplingParams

prompts = [
    "Hello, my name is",
    "The president of the United States is",
    "The capital of France is",
    "The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)

llm = LLM(model="mistralai/Mixtral-8x7B-Instruct-v0.1", tensor_parallel_size=2, quantization="fp8")

outputs = llm.generate(prompts, sampling_params)

# Print the outputs.
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```

**Performance**: For this PR, the focus is on making the code clean (while still trying to get reasonable performance), there is a bunch of optimizations that we will submit as a follow up PR that significantly improve the performance (similar to the numbers in https://github.com/vllm-project/vllm/pull/3954). With this PR, the results are as follows:

<img width="725" alt="Screenshot 2024-04-21 at 1 31 50 PM" src="https://github.com/vllm-project/vllm/assets/113316/d8fe1118-07a0-4d4e-8530-37a77d465a03">


**Accuracy**: The accuracy with this PR on MMLU on `mistralai/Mixtral-8x7B-v0.1` is as follows:

```
|      Groups      |Version|Filter|n-shot|Metric|Value |   |Stderr|
|------------------|-------|------|-----:|------|-----:|---|-----:|
|mmlu              |N/A    |none  |     0|acc   |0.7018|±  |0.0036|
| - humanities     |N/A    |none  |     5|acc   |0.6472|±  |0.0065|
| - other          |N/A    |none  |     5|acc   |0.7673|±  |0.0072|
| - social_sciences|N/A    |none  |     5|acc   |0.8099|±  |0.0070|
| - stem           |N/A    |none  |     5|acc   |0.6131|±  |0.0083|
```
this compares favorably with the fp16 results which are
```
|      Groups      |Version|Filter|n-shot|Metric|Value |   |Stderr|
|------------------|-------|------|-----:|------|-----:|---|-----:|
|mmlu              |N/A    |none  |     0|acc   |0.7020|±  |0.1313|
| - humanities     |N/A    |none  |     5|acc   |0.6425|±  |0.1349|
| - other          |N/A    |none  |     5|acc   |0.7744|±  |0.1038|
| - social_sciences|N/A    |none  |     5|acc   |0.8131|±  |0.0695|
| - stem           |N/A    |none  |     5|acc   |0.6108|±  |0.1383|
```

Happy hacking!

Co-authored-by: mgoin <michael@neuralmagic.com>

Provide an initial support to FP8 computation. This PR is inspired by HuggingFace TGI: huggingface/text-generation-inference#1726

This feature can be enabled with --quantization fp8 or -q fp8 when launching an engine.

Algorithm:
We still load a model checkpoint in FP16/BF16. After the weights are loaded, Fp8LinearMethod calculates the per-tensor scaling factor of weights and quantizes the weights accordingly. The scaling factor will then be stored for future use. Meanwhile, the per-tensor scaling factor for activations is calculated in every forward pass.

Initial Results:
Currently tested Mistral-7B on 1xH100. With prompt length ~5 and decoding length 128:

BF16: 1.47s
FP8: 1.66s
I'll try to use larger models and try to find more performance bottleneck. Meanwhile, you're welcome to try this code.

Co-authored-by: Ubuntu <ubuntu@ip-172-31-13-147.ec2.internal>

Co-authored-by: SangBin Cho <sangcho@sangcho-LT93GQWG9C.local>

Co-authored-by: Simon Mo <simon.mo@hey.com>

Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>

Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>