FazBrowse GitHub Viewer | Trending | | Home

Tools: [Download Repo ZIP] [Original HTTPS Page]

History for llama_cpp/server - KoolSameer/llama-cpp-python · GitHub

Commits

History for

Commits on Jul 9, 2023

bugfix: pydantic settings missing / changed fields
abetlen
committed
6f70cc4

Commits on Jul 8, 2023

Upgrade fastapi to 0.100.0 and pydantic v2
abetlen
committed
52753b7

Commits on Jul 7, 2023

Add setting to control request interruption
abetlen
committed
57d8ec3
Add interruptible streaming requests for llama-cpp-python server. Closes #183
abetlen
committed
4c7cdcc

Commits on Jun 22, 2023

server: pass seed param from command line to llama
lexin4ever
authored
282698b

Commits on Jun 15, 2023

Add low_vram to server settings
abetlen
committed
1e20be6
Format server options
abetlen
committed
f7c5cfa
Merge branch 'main' of github.com:abetlen/llama_cpp_python into main
abetlen
committed
9c41a3e
Merge pull request #351 from player1537-forks/th/add-logits-bias-parameter
abetlen
authored
f568bae
Add additional verbose logs for cache
abetlen
committed
f27393a

Commits on Jun 11, 2023

correction to add back environment variable support <3 docker
Orfeous
committed
3129a0e

Commits on Jun 10, 2023

fixes abetlen/llama-cpp-python #358
Orfeous
committed
3ea3193

Commits on Jun 9, 2023

Add support for logit_bias and logit_bias_type parameters
player1537
committed
eb7645b

Commits on Jun 8, 2023

Fix cache implementation breaking changes
abetlen
committed
0c42168

Commits on Jun 6, 2023

Added mirostat support for completions, chat completions API
spirilis
committed
9b1c9e9

Commits on May 27, 2023

Use async routes
abetlen
committed
80066f0
Import unnused import
abetlen
committed
c2b59a5

Commits on May 19, 2023

feat: make embedding support list of string as input
chabotsi
committed
e783f1c
Bugfix: Stop sequences can be strings
abetlen
committed
a8cd169
Use server sent events function for streaming completion
abetlen
committed
dc39cc0

Commits on May 16, 2023

Add model_alias option to override model_path in completions. Closes #39
abetlen
committed
a335292

Commits on May 14, 2023

Update llama.cpp
abetlen
committed
cdf5976

Commits on May 12, 2023

Only support generating one prompt at a time.
abetlen
committed
8740ddc
Revert "llama_cpp server: prompt is a string". Closes #187
abetlen
committed
8895b90

Commits on May 9, 2023

llama_cpp server: document presence_penalty and frequency_penalty, mark as supported
Stonelinks
committed
02e8a01

Commits on May 8, 2023

Fix: default repeat_penalty
abetlen
committed
82d138f
Bugfix: not falling back to environment variables when default is value is set.
abetlen
committed
29f094b
Show default value when --help is called
abetlen
committed
0d6c600
Use environment variable if parsed cli arg is None
abetlen
committed
022e9eb
Set repeat_penalty to 0 by default
abetlen
committed
0d751a6
Add openai frequency and presence penalty parameters. Closes #169
abetlen
committed
65d9cc0
Bugfix for models endpoint
abetlen
committed
a0b61ea

Commits on May 7, 2023

Added cache size to settins object.
abetlen
committed
14da46f
Add verbose flag to server
abetlen
committed
627811e
Fix mlock_supported and mmap_supported return type
abetlen
committed
3fbda71

Back | FazBrowse Home | New Git URL