[pull] main from vllm-project:main #5
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
![pull[bot]](https://avatars.githubusercontent.com/in/12910?s=60&v=4){kind=small}
Signed-off-by: Tao He <sighingnow@gmail.com>
…he revision parameter (#4217)
Co-authored-by: Harry Mellor <hmellor@oxts.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
This PR is the first step towards fixing #3208 It implements dynamic per-tensor scaling (see #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 #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!
Fixes fp8 iterface which broke in AQLM merge.
[Core][Distributed] use existing torch.cuda.device context manager (#4318)
This PR addresses the Marlin kernel H100 crash that was reported here: neuralmagic#187. The reason for the crash was the inline PTX assembly that introduced the async_copy with streaming behavior. The solution is to use the more standard PTX for async_copy (without the fractional L2 policy for "evict_first"). There is no performance difference between standard async_copy PTX and the previous one.
|
Hi @pull[bot]. Thanks for your PR. I'm waiting for a opendatahub-io member to verify that this patch is reasonable to test. If it is, they should reply with Once the patch is verified, the new status will be reflected by the I understand the commands that are listed here. Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository. |
Co-authored-by: Simon Mo <simon.mo@hey.com>
…formers 4.40.0 (#4324) Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Caio Mendes <caiocesart@microsoft.com>
Co-authored-by: WoosukKwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Danny Guinther <dguinther@neuralmagic.com>
|
/lgtm |
|
/ok-to-test |
|
/lgtm |
|
/approve |
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: pull[bot], Xaenalt The full list of commands accepted by this bot can be found here.
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
See Commits and Changes for more details.
Created by
pull[bot]
Can you help keep this open source service alive? 💖 Please sponsor : )