issues
search
Blaizzy
/
fastmlx
FastMLX is a high performance production ready API to host MLX models.
Other
148
stars
11
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Future: add image generation prompts?
#31
stewartugelow
opened
2 days ago
0
Using OpenAI API compliant to support vision models
#30
madroidmaq
opened
2 days ago
0
Multiple workers do not share memory, which causes a full model reload for each message generation.
#29
ZachZimm
opened
3 days ago
0
Integrate mlx-hub like functionality?
#28
stewartugelow
opened
6 days ago
2
Implement Token Usage Tracking
#27
ZachZimm
opened
1 week ago
4
Memory leak ?
#26
iLoveBug
opened
2 weeks ago
7
Fix tools template loader (Jinja 2 Template not found)
#25
Blaizzy
closed
2 weeks ago
0
Implement CLI Client for FastMLX
#24
Blaizzy
opened
4 weeks ago
0
FastMLX Python Client
#23
Blaizzy
opened
4 weeks ago
3
Implement role:system in messages
#22
pablo-mano
closed
4 weeks ago
3
Add support for tool calling
#21
Blaizzy
closed
3 weeks ago
0
How to make it verbose?
#20
namp
opened
1 month ago
3
Add Docs
#19
Blaizzy
opened
1 month ago
2
Feature Request: Integrate Features from Ollama
#18
evertjr
opened
1 month ago
8
Explore integration with exo?
#17
stewartugelow
opened
1 month ago
4
Documentation link is 404
#16
awni
opened
1 month ago
1
feat: Set `workers` through env variable, improved defaults
#15
SiddhantSadangi
closed
1 month ago
2
Potential error in shutdown if manually cancelled
#14
stewartugelow
closed
1 month ago
6
Microsoft Phi 3 EOS token not recognized
#13
stewartugelow
closed
1 month ago
2
(0.1) Uvicorn running on http://0.0.0.0:8000
#12
stewartugelow
closed
1 month ago
2
Weird image URL bug with Wikimedia
#11
stewartugelow
closed
1 month ago
9
Implement Error Handling for Unsupported Model Types
#10
Blaizzy
opened
1 month ago
0
Implement Model Loading State Tracker
#9
Blaizzy
opened
1 month ago
0
Implement Basic Token Usage Tracking
#8
Blaizzy
opened
1 month ago
1
Add Parallel calls usage
#7
Blaizzy
closed
1 month ago
0
No chat template specified for llava models error
#6
stewartugelow
opened
1 month ago
13
max_tokens not overriding the default
#5
stewartugelow
closed
1 month ago
1
Add support for token streaming, parallel jobs and custom CORS
#4
Blaizzy
closed
1 month ago
0
Documention link is broken
#3
ipfans
opened
1 month ago
1
Cross origin support
#2
digicali
closed
1 month ago
4
Setup FastMLX
#1
Blaizzy
closed
1 month ago
0