Open Issues Need Help
View All on GitHub [MEDIUM] Better placement algorithm for pipeline parallelism using memory bandwidth + latency about 2 months ago
enhancement good first issue
Ring Attention for coupling the data transfer with computation of attention block matrices 2 months ago
enhancement help wanted
docs: Contribute more documentation 3 months ago
enhancement good first issue
Support all MLX backends 9 months ago
enhancement good first issue
enhancement good first issue
[BOUNTY - $200] Batched Requests 10 months ago
good first issue