carlson-svg
|
825ef25b60
|
changed to minimumCudaVersion to camel case
|
2024-08-21 12:47:48 -07:00 |
|
carlson-svg
|
1e9aeb6e8f
|
adding "minimum_cuda_version" to each version
|
2024-08-21 12:44:45 -07:00 |
|
carlson-svg
|
e6172dddd4
|
took out space in imageName from version 0.5.4
|
2024-08-19 15:17:20 -07:00 |
|
carlson-svg
|
21a1e138b4
|
updated version of human readable config
|
2024-08-18 23:57:19 -07:00 |
|
carlson-svg
|
a40e7803ee
|
converted to human readable format
|
2024-08-18 23:24:40 -07:00 |
|
 CarlsonandGitHub
|
5e245793bc
|
Merge pull request #1 from carlson-svg/add-worker-config
v0 worker-config
|
2024-08-13 20:43:47 -07:00 |
|
carlson-svg
|
0ae11ea6df
|
v0 worker-config
|
2024-08-09 15:10:08 -07:00 |
|
 Marut PandyaandGitHub
|
f023f57217
|
Update README.md
|
2024-08-07 15:38:26 -07:00 |
|
 Marut PandyaandGitHub
|
673597fd46
|
Update README.md
|
2024-08-07 15:32:23 -07:00 |
|
 Marut PandyaandGitHub
|
c50543ebd9
|
Update README.md
|
2024-08-07 15:30:33 -07:00 |
|
 Marut PandyaandGitHub
|
17a2d844ec
|
Merge pull request #93 from runpod-workers/up-rdme
Update README.md
|
2024-08-05 14:36:39 -07:00 |
|
pandyamarut
|
3498e99b2f
|
update
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
|
2024-08-05 14:33:56 -07:00 |
|
pandyamarut
|
5da96ce9a6
|
update
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
|
2024-08-05 14:26:56 -07:00 |
|
 Marut PandyaandGitHub
|
e32626ca9d
|
Update README.md
|
2024-08-05 14:19:38 -07:00 |
|
 Marut PandyaandGitHub
|
37d140aba6
|
Update docker-bake.hcl
v1.1
|
2024-08-02 16:53:59 -07:00 |
|
 Marut PandyaandGitHub
|
66ed2a2a5f
|
Merge pull request #90 from runpod-workers/pandyamarut-patch-1
Update README.md
|
2024-08-02 16:03:18 -07:00 |
|
pandyamarut
|
e846ecae9d
|
update readme
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
|
2024-08-02 14:13:55 -07:00 |
|
 Marut PandyaandGitHub
|
9f066be620
|
Update README.md
|
2024-08-02 13:29:18 -07:00 |
|
 Marut PandyaandGitHub
|
8a010c3804
|
Merge pull request #82 from runpod-workers/any-arg-and-refactor
Allow any vLLM engine args as env vars, Update vLLM, refactor
|
2024-08-01 15:28:11 -07:00 |
|
pandyamarut
|
14cacd55fe
|
update docker
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
|
2024-07-31 18:44:46 -07:00 |
|
 Marut PandyaandGitHub
|
e1b41795f7
|
Update README.md
|
2024-07-31 12:46:34 -07:00 |
|
 Marut PandyaandGitHub
|
0814d76654
|
Update README.md
|
2024-07-30 17:09:01 -07:00 |
|
pandyamarut
|
f3534a4ea7
|
fix openai compat
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
|
2024-07-27 15:49:45 -07:00 |
|
 Marut PandyaandGitHub
|
b61ea5ea46
|
Delete test.py
|
2024-07-26 17:32:16 -07:00 |
|
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 |
|