 pandyamarut
|
0f8657e58d
|
update env default args
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
|
2024-07-26 16:52:51 -07:00 |
|
|
pandyamarut
|
bd96b5e0de
|
update v0.5.3.post1
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
|
2024-07-25 21:29:45 -07:00 |
|
|
alpayariyak
|
5bd6f3a75e
|
0.5.3, any vllm arg as env var, refactor and fixes, moving away from building separate image from vLLM fork
|
2024-07-25 12:41:48 -07:00 |
|
|
alpayariyak
|
a08d83f600
|
Allow any vLLM engine args as env vars, refactor
|
2024-07-02 19:44:01 +00:00 |
|
|
alpayariyak
|
0e1e38326a
|
Fix deprecated max_context_len_to_capture engine argument
1.0.1
|
2024-06-13 17:48:05 +00:00 |
|
|
alpayariyak
|
c8458fef2b
|
preparation for 1.0.0 release
1.0.0
|
2024-06-12 12:28:03 -07:00 |
|
|
alpayariyak
|
bad5ddd892
|
Fix vLLM 0.4.1 bug for OpenAI /models route
|
2024-06-10 20:38:49 +00:00 |
|
|
alpayariyak
|
f19ce12ab0
|
Fix Building Docker with model built-in #71
|
2024-06-07 15:29:46 -07:00 |
|
|
alpayariyak
|
1bb6f84541
|
Deprecated kv cache dtype warning
|
2024-05-10 16:29:20 +00:00 |
|
|
|
30cb56a3df
|
Fix MODEL_REVISION env var (Merge pull request #50 from joennlae/rename-revision and #67 from mikljohansson/main)
Fixed MODEL_REVISION environment variable
Co-Authored-By: Jannis Schönleber <1493766+joennlae@users.noreply.github.com>
Co-Authored-By: Mikael Johansson <mikl.johansson@gmail.com>
|
2024-05-09 20:45:07 -04:00 |
|
|
alpayariyak
|
00add8707a
|
Temporarily disable build and push github actions
|
2024-05-09 20:33:52 -04:00 |
|
|
alpayariyak
|
ec7ea0b760
|
Update default base image version to fix github actions build
|
2024-05-09 20:18:34 -04:00 |
|
|
alpayariyak
|
9f2cb7b1d0
|
Update documentation to include rename of fp8_e5m2 to fp8
|
2024-05-09 23:59:11 +00:00 |
|
|
alpayariyak
|
4abe494635
|
Fix hf-transfer error
|
2024-05-09 23:51:07 +00:00 |
|
|
Alpay AriyakandGitHub
|
4f61b04afe
|
Update README.md
|
2024-05-09 01:05:04 -04:00 |
|
|
Alpay Ariyakandalpayariyak
|
874379a0c5
|
1.0.0preview update for Llama 3 support and more (vLLM 0.3.3 -> 0.4.2) (#62)
|
2024-05-09 00:42:08 -04:00 |
|
|
Mikael Johansson
|
f06a64d5b9
|
Fixed MODEL_REVISION environment variable
|
2024-05-02 13:45:43 +02:00 |
|
|
alpayariyak
|
0a5b5bc095
|
Add badges
|
2024-03-15 21:23:52 -04:00 |
|
|
alpayariyak
|
2936e4d95d
|
Update automatic builds, documentation
|
2024-03-15 11:57:38 -04:00 |
|
|
Alpay AriyakandGitHub
|
cee4e484d5
|
Update README.md for 0.3.2
0.3.2
|
2024-03-12 19:07:37 -04:00 |
|
|
Alpay AriyakandGitHub
|
6160769996
|
Release 0.3.2
|
2024-03-12 17:44:47 -05:00 |
|
|
alpayariyak
|
d25b6f9628
|
Fix sampling params
|
2024-03-12 22:15:57 +00:00 |
|
|
alpayariyak
|
c8ee100d80
|
Small refactor
|
2024-03-06 17:08:57 +00:00 |
|
|
alpayariyak
|
fee8d8eee4
|
Fix submodule
|
2024-03-05 19:17:53 +00:00 |
|
|
alpayariyak
|
db7167d57f
|
0.3.3
|
2024-03-05 19:14:35 +00:00 |
|
|
Alpay Ariyakandalpayariyak
|
d91ccb866f
|
0.3.1: bug fixes
0.3.1
|
2024-02-29 02:55:44 -05:00 |
|
|
Alpay AriyakandGitHub
|
36e9b670ee
|
Add notice on what to do when HuggingFace is down
|
2024-02-28 17:10:39 -05:00 |
|
|
Alpay Ariyakandalpayariyak
|
91167b873a
|
v0.3.0: OpenAI Compatibility, Dynamic Stream Batching, Refactor, Error Catching
0.3.0
|
2024-02-23 22:34:00 -05:00 |
|
|
alpayariyak
|
819102cfd6
|
Merge branch 'openai-sse-output' of https://github.com/runpod-workers/worker-vllm into openai-sse-output
|
2024-02-24 03:18:37 +00:00 |
|
|
alpayariyak
|
985bbf1cb5
|
Fix Multi-GPU, tokenizer trust remote code
|
2024-02-24 03:18:25 +00:00 |
|
|
Alpay AriyakandGitHub
|
6f5718f191
|
Update Docker image tag in README.md
|
2024-02-23 02:15:50 -05:00 |
|
|
Alpay AriyakandGitHub
|
235d0d31d0
|
Merge pull request #50 from runpod-workers/tagged-releases
feat: auto build cuda version
|
2024-02-22 23:14:57 -05:00 |
|
|
alpayariyak
|
708f68d7f8
|
Final Bug fixes, configurable oai response role, served model name override, documentation
|
2024-02-23 04:14:03 +00:00 |
|
|
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 |
|