- 07 May, 2025 2 commits
-
-
Bowen Bao authored
-
Jee Jee Li authored
Signed-off-by:Jee Jee Li <pandaleefree@gmail.com>
-
- 24 Apr, 2025 1 commit
-
-
Harry Mellor authored
Signed-off-by:Harry Mellor <19981378+hmellor@users.noreply.github.com>
-
- 23 Apr, 2025 1 commit
-
-
Harry Mellor authored
Signed-off-by:Harry Mellor <19981378+hmellor@users.noreply.github.com>
-
- 01 Apr, 2025 1 commit
-
-
Harry Mellor authored
Signed-off-by:Harry Mellor <19981378+hmellor@users.noreply.github.com>
-
- 31 Mar, 2025 1 commit
-
-
Harry Mellor authored
Signed-off-by:Harry Mellor <19981378+hmellor@users.noreply.github.com>
-
- 26 Mar, 2025 1 commit
-
-
Harry Mellor authored
Signed-off-by:
Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by:
Isotr0py <2037008807@qq.com> Co-authored-by:
Isotr0py <2037008807@qq.com> Co-authored-by:
Isotr0py <mozf@mail2.sysu.edu.cn>
-
- 24 Mar, 2025 1 commit
-
-
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 authored
Signed-off-by:Hollow Man <hollowman@opensuse.org>
-
- 15 Mar, 2025 1 commit
-
-
Robert Shaw authored
Signed-off-by:
rshaw@neuralmagic.com <rshaw@neuralmagic.com> Co-authored-by:
rshaw@neuralmagic.com <rshaw@neuralmagic.com> Co-authored-by:
Nicolò Lucchesi <nlucches@redhat.com> Co-authored-by:
Tyler Michael Smith <tyler@neuralmagic.com> Co-authored-by:
Michael Goin <michael@neuralmagic.com>
-
- 18 Feb, 2025 1 commit
-
-
Isotr0py authored
Signed-off-by:Isotr0py <2037008807@qq.com>
-
- 05 Feb, 2025 1 commit
-
-
Kyle Sayers authored
Signed-off-by:
mgoin <michael@neuralmagic.com> Signed-off-by:
Kyle Sayers <kylesayrs@gmail.com> Co-authored-by:
mgoin <michael@neuralmagic.com>
-
- 04 Feb, 2025 1 commit
-
-
Jee Jee Li authored
Signed-off-by:Jee Jee Li <pandaleefree@gmail.com>
-
- 03 Feb, 2025 1 commit
-
-
Arthur authored
# Adds support for `transformers` as a backend Following https://github.com/huggingface/transformers/pull/35235 , a bunch of models should already be supported, we are ramping up support for more models. Thanks @Isotr0py for the TP support, and @hmellor for his help as well! This includes: - `trust_remote_code=True` support: any model on the hub, if it implements attention the correct way can be natively supported!! - tensor parallel support --------- Signed-off-by:
Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by:
Isotr0py <2037008807@qq.com> Co-authored-by:
Isotr0py <41363108+Isotr0py@users.noreply.github.com> Co-authored-by:
Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by:
Isotr0py <2037008807@qq.com> Co-authored-by:
Cyrus Leung <cyrus.tl.leung@gmail.com> Co-authored-by:
Michael Goin <mgoin64@gmail.com> Co-authored-by:
Isotr0py <mozf@mail2.sysu.edu.cn>
-
- 02 Feb, 2025 1 commit
-
-
Russell Bryant authored
- **Add SPDX license headers to python source files** - **Check for SPDX headers using pre-commit** commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745 Author: Russell Bryant <rbryant@redhat.com> Date: Fri Jan 31 14:18:24 2025 -0500 Add SPDX license headers to python source files This commit adds SPDX license headers to python source files as recommended to the project by the Linux Foundation. These headers provide a concise way that is both human and machine readable for communicating license information for each source file. It helps avoid any ambiguity about the license of the code and can also be easily used by tools to help manage license compliance. The Linux Foundation runs license scans against the codebase to help ensure we are in compliance with the licenses of the code we use, including dependencies. Having these headers in place helps that tool do its job. More information can be found on the SPDX site: - https://spdx.dev/learn/handling-license-info/ Signed-off-by:Russell Bryant <rbryant@redhat.com> commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea Author: Russell Bryant <rbryant@redhat.com> Date: Fri Jan 31 14:36:32 2025 -0500 Check for SPDX headers using pre-commit Signed-off-by:
Russell Bryant <rbryant@redhat.com> --------- Signed-off-by:
Russell Bryant <rbryant@redhat.com>
-
- 14 Jan, 2025 1 commit
-
-
Jee Jee Li authored
Signed-off-by:Jee Jee Li <pandaleefree@gmail.com>
-
- 24 Dec, 2024 1 commit
-
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
- 11 Dec, 2024 1 commit
-
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
- 07 Dec, 2024 1 commit
-
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
- 01 Dec, 2024 1 commit
-
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
- 04 Oct, 2024 1 commit
-
-
ElizaWszola authored
Co-authored-by:
Dipika <dipikasikka1@gmail.com> Co-authored-by:
Dipika Sikka <ds3822@columbia.edu>
-
- 16 Sep, 2024 1 commit
-
-
ElizaWszola authored
Co-authored-by:Dipika <dipikasikka1@gmail.com>
-
- 10 Sep, 2024 1 commit
-
-
Dipika Sikka authored
-
- 27 Aug, 2024 1 commit
-
-
Dipika Sikka authored
Co-authored-by:ElizaWszola <eliza@neuralmagic.com>
-
- 22 Aug, 2024 1 commit
-
-
Michael Goin authored
-
- 21 Aug, 2024 1 commit
-
-
Dipika Sikka authored
Co-authored-by:ElizaWszola <eliza@neuralmagic.com>
-
- 06 Aug, 2024 1 commit
-
-
Cyrus Leung authored
Co-authored-by:Roger Wang <136131678+ywang96@users.noreply.github.com>
-
- 24 Apr, 2024 1 commit
-
-
Philipp Moritz authored
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!
-
- 16 Apr, 2024 1 commit
-
-
Antoni Baum authored
-