COMMITS
/ dsp/modules/hf_client.py September 20, 2024
A
Update hf_client.py to support custom headers
arnavsinghvi11 committed
July 16, 2024
Z
fix(mlc-llm): fix mlc-llm ChatModuleClient with MLCEngine
Zhaohan Dong committed
July 10, 2024
A
update import
Arnav Singhvi committed
A
added configurable backoff max time
Arnav Singhvi committed
July 8, 2024
A
Merge pull request #1250 from MohammedAlhajji/main
arnavsinghvi11 committed
M
🐛 fix: http_request_kwargs in HFClientVLLM
Mohammed Alhajji committed
July 7, 2024
H
Update hf_client.py
Haz Sameen Shahgir committed
June 5, 2024
A
fix(dspy): together client response parsing
Adrian Miguel committed
May 28, 2024
A
PR comments
Alex committed
May 26, 2024
A
Allow to configure Anyscale API in constructor
Alex committed
May 19, 2024
T
Remove redundant keyword removal
Tom Dörr committed
T
Add filtering vllm arguments
Tom Dörr committed
May 15, 2024
A
Update hf_client.py
arnavsinghvi11 committed
May 14, 2024
O
bug(dspy): Added the space
Omkar Uttarwar committed
O
bug(dspy): Added the space
Omkar Uttarwar committed
May 12, 2024
O
bug(dspy): Added comments
Omkar Uttarwar committed
O
bug(dspy): fixed the code with the pop method
Omkar Uttarwar committed
O
bug(dspy): fixed the code
Omkar Uttarwar committed
May 11, 2024
O
bug(dspy): removed extra params from kwargs sent to vllm pydantic model
Omkar Uttarwar committed
April 21, 2024
M
Fixed VLLM Cache Fully
Michael Ryan committed
M
Fixed VLLM cache to ignore the url of the request
Michael Ryan committed
April 16, 2024
A
Merge pull request #811 from EmbeddedLLM/vllm-chat
arnavsinghvi11 committed
April 15, 2024
T
update vllm initializtion and fix inspect history
tjtanaa committed
April 13, 2024
T
added vllm chat completion endpoints and fix inspect_history
tjtanaa committed
A
Merge pull request #172 from GuyAglionby/guyaglionby-fix-hf-kwargs
arnavsinghvi11 committed
April 5, 2024
A
Merge pull request #773 from stanfordnlp/curieo-org-initial-groq-support
arnavsinghvi11 committed
March 26, 2024
S
making the fix
Somesh committed
March 15, 2024
S
adding the together fix
Somesh Fengade committed
April 4, 2024
R
fix(dsp): in HFClientVLLM, merge self.kwargs instead of overwriting it
Rémi Connesson committed
April 3, 2024
R
fix(dsp): get the model from the kwargs attached by the parent class
Rémi Connesson committed
March 25, 2024
R
fix(dsp): Append `kwargs` to the payload for vllm
Rémi Connesson committed
R
fix(dsp): Allow optional parameters to be optional
Rémi Connesson committed
R
fix(dsp): use the model declared in the constructor
Rémi Connesson committed
R
fix(dsp): attach `kwargs` to HFClientVLLM instance
Rémi Connesson committed
March 20, 2024
U
Removed unnecessary removal of `/v1/*` from urls passed to `HFClientVLLM`.
Umar Butler committed
March 13, 2024
U
Added support for multiple API endpoints to `HFClientVLLM`
Umar Butler committed
March 4, 2024
I
ci(dspy): Add Ruff linting workflow (#538)
Isaac Miller committed
March 1, 2024
T
Big reformat push
Thomas D Ahle committed
February 11, 2024
P
fix: manually iterate kwargs['n'] in anyscale
Patricio Cerda Mardini committed
February 4, 2024
I
Update the instruction model checking for prompt template
Insop Song committed
I
Update the stop sequence as per Omar's suggestion
Insop Song committed
February 3, 2024
I
Update together model prompt and stop sequence
Insop Song committed
February 2, 2024
I
Add code to acce together APIs
Insop Song committed
January 23, 2024
A
Update hf_client.py
arnavsinghvi11 committed
January 4, 2024
L
add sgalng backend
Lianmin Zheng committed
November 20, 2023
C
add minimum working support for vLLM
Carlo Nucera committed
October 31, 2023
A
update Anyscale client to support default completion-based formatting for models
Arnav Singhvi committed
October 25, 2023
O
Merge pull request #186 from stanfordnlp/anyscale_client
Omar Khattab committed
O
Merge branch 'main' into local_model_loading_TGI
Omar Khattab committed
A
added support for OpenAI completion API string prompting
Arnav Singhvi committed