forked from vllm-project/vllm
-
Notifications
You must be signed in to change notification settings - Fork 48
Insights: ROCm/vllm
Overview
-
- 2 Merged pull requests
- 3 Open pull requests
- 0 Closed issues
- 1 New issue
There hasn’t been any commit activity on ROCm/vllm in the last week.
Want to help out?
2 Pull requests merged by 2 people
-
[FEAT] Support Triton MRoPE kernel
#621 merged
Aug 13, 2025 -
[1/N][port from deepseek085] add custom allreduce from AITER
#629 merged
Aug 12, 2025
3 Pull requests opened by 3 people
-
[Pending][Fix] Shuffle weight and refine the quark MXFP4 kernel dispatch routine
#630 opened
Aug 12, 2025 -
Updated README.md for August 12 RC2 throughput results only
#631 opened
Aug 13, 2025 -
Integrate mxfp4 MoE native kernels
#632 opened
Aug 15, 2025
1 Issue opened by 1 person
-
[QUESTION]: is strix halo gfx1151 support planned? and eta?
#633 opened
Aug 15, 2025
2 Unresolved conversations
Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.
-
[Bug]: Multinode serving with Ray not working due to cupy
#591 commented on
Aug 14, 2025 • 0 new comments -
add fused fp8 bmm
#604 commented on
Aug 13, 2025 • 0 new comments