iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
5,799 Commits 3 Branches 0 Tags
57504a4bcf82cf544a4261778fc0505e492e4484
Commit Graph
47 Commits
Author SHA1 Message Date
Chengji Yao 1621b25288 [TPU] Fix dummy loading OOM (#16372) 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
 2025-04-10 04:06:16 +00:00
Manish Sethi 761702fd19 [Core] Integrate fastsafetensors loader for loading model weights (#10647) 
Signed-off-by: Manish Sethi <Manish.sethi1@ibm.com>
 2025-03-24 08:08:02 -07:00
Aaron Pham 0b7f06b447 [Misc] add use_tqdm_on_load to reduce logs (#14407) 
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
 2025-03-08 05:57:46 -08:00
Jee Jee Li 6a84164add [Bugfix] Add file lock for ModelScope download (#14060) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-03-01 06:10:28 +00:00
Szymon Ożóg 7f0be2aa24 [Model] Deepseek GGUF support (#13167) 2025-02-27 02:08:35 -08:00
Kevin H. LuuandEC2 Default User 473f51cfd9 [3/n][CI] Load Quantization test models with S3 (#13570) 
Signed-off-by: <>
Co-authored-by: EC2 Default User <ec2-user@ip-172-31-20-117.us-west-2.compute.internal>
 2025-02-20 10:12:30 +08:00
Kevin H. LuuandEC2 Default User d5d214ac7f [1/n][CI] Load models in CI from S3 instead of HF (#13205) 
Signed-off-by: <>
Co-authored-by: EC2 Default User <ec2-user@ip-172-31-20-117.us-west-2.compute.internal>
 2025-02-19 07:34:59 +00:00
Nick Hill 9076325677 [BugFix] Don't scan entire cache dir when loading model (#13302) 2025-02-14 21:33:31 -08:00
youkaichao b2496bb07f [core] fix sleep mode and pytorch checkpoint compatibility (#13001) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-02-10 13:03:43 +08:00
Jun Duan 011e612d92 [Misc] Log time consumption on weight downloading (#12926) 2025-02-08 09:16:42 +00:00
Russell Bryant e489ad7a21 [Misc] Add SPDX-License-Identifier headers to python source files (#12628) 
- **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>
 2025-02-02 11:58:18 -08:00
Pavani Majetyandmgoin b02fd288b2 [Hardware][NV] Fix Modelopt model loading for k-v-scales for Llama models. (#11787) 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
 2025-01-29 01:46:12 -08:00
Russell Bryant d3d6bb13fb Set weights_only=True when using torch.load() (#12366) 
Signed-off-by: Russell Bryant <rbryant@redhat.com>
 2025-01-24 02:17:30 +00:00
Gregory ShtrasbergandMicah Williamson e97f802b2d [FP8][Kernel] Dynamic kv cache scaling factors computation (#11906) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>
 2025-01-23 18:04:03 +00:00
youkaichao d53575a5f0 [ci] fix gh200 tests (#11919) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-01-10 16:25:17 +08:00
Cyrus LeungandMaxime Fournioux d848800e88 [Misc] Move print_*_once from utils to logger (#11298) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Maxime Fournioux <55544262+mfournioux@users.noreply.github.com>
Co-authored-by: Maxime Fournioux <55544262+mfournioux@users.noreply.github.com>
 2025-01-09 12:48:12 +08:00
Harry Mellor aba8d6ee00 [Doc] Move examples into categories (#11840) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-01-08 13:09:53 +00:00
Cyrus Leung eec906d811 [Misc] Add placeholder module (#11501) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2024-12-26 13:12:51 +00:00
omer-dayan 995f56236b [Core] Loading model from S3 using RunAI Model Streamer as optional loader (#10192) 
Signed-off-by: OmerD <omer@run.ai>
 2024-12-20 16:46:24 +00:00
Aaron Pham 21063c11c7 [CI/Build] drop support for Python 3.8 EOL (#8464) 
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
 2024-11-06 07:11:55 +00:00
Cyrus Leung 390be74649 [Misc] Print stack trace using logger.exception (#9461) 2024-10-17 13:55:48 +00:00
Tyler Michael Smith 7342a7d7f8 [Model] Support Mamba (#6484) 2024-10-11 15:40:06 +00:00
Pavani Majety efcf946a15 [Hardware][NV] Add support for ModelOpt static scaling checkpoints. (#6112) 2024-09-11 00:38:40 -04:00
Patrick von PlatenandMichael Goin 29f49cd6e3 [Model] Allow loading from original Mistral format (#8168) 
Co-authored-by: Michael Goin <michael@neuralmagic.com>
 2024-09-06 17:02:05 -06:00
Isotr0py 12e1c65bc9 [Model] Add AWQ quantization support for InternVL2 model (#7187) 2024-08-20 23:18:57 -07:00
Michael Goin 21313e09e3 [Bugfix] Fix default weight loading for scalars (#7534) 2024-08-15 13:10:22 -07:00
Cyrus Leung 7025b11d94 [Bugfix] Fix weight loading for Chameleon when TP>1 (#7410) 2024-08-13 05:33:41 +00:00
Isotr0py 8334c39f37 [Bugfix] Fix new Llama3.1 GGUF model loading (#7269) 2024-08-08 13:42:44 -07:00
Isotr0pyandMichael Goin 360bd67cf0 [Core] Support loading GGUF model (#5191) 
Co-authored-by: Michael Goin <michael@neuralmagic.com>
 2024-08-05 17:54:23 -06:00
Woosuk Kwon 23993a7997 [Bugfix][TPU] Do not use torch.Generator for TPUs (#6981) 2024-07-31 18:50:28 -07:00
dongmao zhangandMichael Goin 87525fab92 [bitsandbytes]: support read bnb pre-quantized model (#5753) 
Co-authored-by: Michael Goin <michael@neuralmagic.com>
 2024-07-23 23:45:09 +00:00
Simon Mo 3eda4ec780 support ignore patterns in model loader (#6673) 2024-07-22 23:59:42 -07:00
youkaichao c5201240a4 [misc] only tqdm for first rank (#6672) 2024-07-22 21:57:27 -07:00
zhaotyertianyi.zhaoyoukaichao
 		e519ae097a add tqdm when loading checkpoint shards (#6569) 
Co-authored-by: tianyi.zhao <tianyi.zhao@transwarp.io>
Co-authored-by: youkaichao <youkaichao@126.com>
 2024-07-22 20:48:01 -07:00
youkaichao ce37be7ba0 [misc][distributed] add seed to dummy weights (#6491) 2024-07-16 19:16:34 -07:00
Michael Goin 978aed5300 [Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (#6081) 2024-07-16 15:31:32 -07:00
Robert Shaw 73030b7dae [ Misc ] Enable Quantizing All Layers of DeekSeekv2 (#6423) 2024-07-14 21:38:42 +00:00
Cyrus Leung 0e9164b40a [mypy] Enable type checking for test directory (#5017) 2024-06-15 04:45:31 +00:00
Dipika SikkaandMichael Goin 5884c2b454 [Misc] Update to comply with the new compressed-tensors config (#5350) 
Co-authored-by: Michael Goin <michael@neuralmagic.com>
 2024-06-10 03:49:46 +00:00
chenqianfzh b9c0605a8e [Feature][Kernel] Support bitsandbytes quantization and QLoRA (#4776) 2024-06-01 14:51:10 -06:00
Robert ShawandCody Yu 919770957f [Bugfix] Fix Mistral v0.3 Weight Loading (#5005) 
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
 2024-05-24 12:28:27 +00:00
Dipika SikkaVarun Sundar RabindranathVarun Sundar Rabindranath
 		a1242324c9 [Kernel] Initial Activation Quantization Support (#4525) 
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
 2024-05-23 21:29:18 +00:00
Mor ZusmanandMor Zusman f0eecee610 [Bugfix] Fix dummy weight for fp8 (#4916) 
Allow dummy load format for fp8,
torch.uniform_ doesn't support FP8 at the moment

Co-authored-by: Mor Zusman <morz@ai21.com>
 2024-05-20 18:44:25 +00:00
Prashant GuptaandTravis Johnson d6e520e170 [Core] Support offline use of local cache for models (#4374) 
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
Co-authored-by: Travis Johnson <tjohnson31415@gmail.com>
 2024-04-27 09:59:55 -07:00
SangBin ChoandDanny Guinther a88081bf76 [CI] Disable non-lazy string operation on logging (#4326) 
Co-authored-by: Danny Guinther <dguinther@neuralmagic.com>
 2024-04-26 00:16:58 -07:00
Cody Yu a22cdea371 [Kernel][FP8] Initial support with dynamic per-tensor scaling (#4118) 
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.
 2024-04-20 04:28:57 +00:00
Antoni Baum 69e1d2fb69 [Core] Refactor model loading code (#4097) 2024-04-16 11:34:39 -07:00