owen/worker-vllm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
364 Commits 1 Branch 69 Tags
b8fb31348390239deeca61ec6975edece2baec93
Commit Graph
364 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
alpayariyak b42d45ce0f Bug fixes, refactors 2024-02-23 03:46:47 +00:00
Justin Merrell 7221caceff feat: auto build cuda version 2024-02-22 20:48:54 -05:00
alpayariyak a2d9535652 Update documentation further 2024-02-23 01:34:38 +00:00
alpayariyak 9129d0a252 New ENV Vars 2024-02-22 23:58:20 +00:00
alpayariyak 6bcd9d7c67 Preparing for 0.3.0 2024-02-22 18:04:34 -05:00
Alpay AriyakandGitHub b4204c612c Merge pull request #48 from rachfop/patch-1 
Fixes import statement in docs
 2024-02-21 23:55:11 -05:00
Patrick RachfordandGitHub 7993818f5f Update README.md 
Remove formatting of tables
 2024-02-21 19:28:03 -08:00
Patrick RachfordandGitHub e97917cc14 Fixes import statement 
Fixes import statements, formats tables, run black on code blocks
 2024-02-21 19:17:23 -08:00
Alpay AriyakandGitHub 3549cf24d5 Merge branch 'main' into openai-sse-output 2024-02-21 19:56:55 -05:00
alpayariyak aed0408f19 Documentation for 0.3.0, small fixes and changes 2024-02-21 19:28:59 -05:00
alpayariyak e191149259 OpenAI Compatibility, Dynamic Batching, Refactor 2024-02-21 04:36:04 +00:00
Alpay AriyakandGitHub 2941db0fb8 Update worker-vllm version 0.2.3 2024-02-09 23:12:29 -05:00
Alpay AriyakandGitHub bfeb60c54e Merge pull request #45 from willsamu/fix-tokenizer-input 
fix: build error if no `TOKENIZER_NAME` provided
 2024-02-09 22:51:18 -05:00
alpayariyak 7b3fd05542 Small refactor to tokenizer fix 2024-02-09 22:50:00 -05:00
Samuel Will b0e7b575f3 fix: default value for tokenizer 2024-02-09 10:24:58 +00:00
alpayariyak 4f5e0d37c4 Fix tokenizer's trust_remote_code parameter 2024-02-08 23:53:13 +00:00
alpayariyak a94ef66f71 Dynamic Batch Size [needs refactor] 2024-02-06 03:47:27 +00:00
alpayariyak 45081e4037 Add __init__.py 2024-02-06 02:44:35 +00:00
alpayariyak fef8c81cb9 OpenAI Compatible worker, Refactor 2024-02-06 02:44:14 +00:00
alpayariyak 15b06bb687 Merge branch 'main' into openai-sse-output 2024-02-02 20:03:29 -05:00
Alpay AriyakandGitHub 2b5b8dfb61 Fix Model and Tokenizer download for bake-in option, add revision configuration for both. 2024-02-02 19:58:50 -05:00
alpayariyak 8de10468dd Working tokenizer and model download fix 
Fix handler startup
 2024-02-02 19:55:35 -05:00
alpayariyak b7051d37ca Move test_openai_stream.py 2024-02-02 22:12:26 +00:00
alpayariyak b1720a154d Added download of model extras into weights folder, separate download of tokenizer, making engine.py utilize downloaded tokenizer, model and tokenizer revision 2024-01-31 22:57:32 -05:00
alpayariyak afa33a2875 Handle errors 2024-02-01 03:01:51 +00:00
alpayariyak 068303ce8f OpenAI Proxy Server for EndPoints and more examples 2024-02-01 02:32:32 +00:00
alpayariyak 3bbcf0021b Fix: Yield if tokens left in batch 
Temp: default model for testing image
 2024-02-01 00:52:39 +00:00
alpayariyak dab8bad906 OpenAI Chat Completions Stream 2024-01-31 23:27:31 +00:00
Casper f4d7c75504 Snapshot download only tokenizer/config related things 2024-01-31 22:16:44 +01:00
Casper 3adc9e3336 Remove unused import 2024-01-31 18:27:49 +01:00
Casper fd00a1ece3 Update to use snapshot_download 2024-01-31 18:24:57 +01:00
Casper 664dd35782 Download tokenizer upon build 2024-01-31 17:59:52 +01:00
alpayariyak 370698442c Update RunPod SDK version and Docker Tag 2024-01-31 00:54:58 -05:00
alpayariyak 3e2cd080a2 Fix Tensor Parallel 0.2.2 2024-01-31 05:12:58 +00:00
alpayariyak e7b340d73b Update vLLM base image 2024-01-31 03:37:55 +00:00
alpayariyak 46eee12819 Simplify Tensor Parallel 2024-01-31 03:28:02 +00:00
alpayariyak 12d6f0778e Fixed Model bake-in, added Custom Chat Templates, Custom Tokenizer 2024-01-31 03:13:21 +00:00
Alpay AriyakandGitHub fa5556434c Bug fix 2024-01-29 11:26:22 -05:00
alpayariyak 97726372c0 Update release tag in README.md 2024-01-25 23:37:07 -05:00
alpayariyak 9fc8e1e54c Non-streaming OpenAI Chat Completions 0.2.1 2024-01-25 23:24:18 -05:00
alpayariyak 4cebe66b36 0.2.0 Release 
- You no longer need a linux-based machine or NVIDIA GPUs to build the worker.
- Over 3x lighter Docker image size.
- OpenAI Chat Completion output format (optional to use).
- Extremely fast image build time.
- Docker Secrets-protected Hugging Face token support for building the image with a model baked in without exposing your token.
- Support for `n` and `best_of` sampling parameters, which allow you to generate multiple responses from a single prompt.
- New environment variables for various configuration.
- vLLM Version: 0.2.7
0.2.0 		2024-01-25 20:49:15 -05:00
Alpay Ariyakandalpayariyak 368c5f87fb Temporary Dockerfile Fix 
Temporary Dockerfile fix
 2024-01-25 20:48:26 -05:00
alpayariyak 15cc7cd36f Updated Documentation 2024-01-19 10:48:12 -05:00
alpayariyak ef3c303743 Added support for n parameter 2024-01-19 15:34:25 +00:00
alpayariyak 584852f0f6 Docker-Protected HF Token, Refactor, Better Documentation 2024-01-18 18:20:51 -05:00
Alpay AriyakandGitHub 65454c024a Update README.md (temporary) 2024-01-17 00:16:56 -05:00
Justin Merrell f023e2e097 Update README.md 2024-01-16 19:55:20 -05:00
Alpay AriyakandGitHub ed48093792 bug fix 0.1.0 2024-01-16 18:38:26 -05:00
alpayariyak a5dc8b53b7 Fix Concurrency, Add Max Model Length 2024-01-16 17:58:46 -05:00
Justin Merrell 6e7a1953e4 fix: update runpod package 2024-01-12 09:26:08 -05:00