-
Notifications
You must be signed in to change notification settings - Fork 314
Pull requests: vllm-project/recipes
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[ROCm][AMD] MiniMax-M3 MXFP8 MI355x recipe update
#581
opened Jun 26, 2026 by
hongxiayang
Contributor
Loading…
Add MiniMax-M3 MXFP4 (AMD) variant
#579
opened Jun 25, 2026 by
andyluo7
Contributor
Loading…
3 tasks done
fix(google/gemma-4-26b-a4b-it): add --max-num-batched-tokens to single-GPU command
#572
opened Jun 22, 2026 by
mahadrehmann
Loading…
fix: add timeouts to build-time network requests
#570
opened Jun 18, 2026 by
MatrixNeoKozak
Loading…
[AMD] MiniMax-M3: enable AITER + AMD runtime knobs in the ROCm hardware override
#556
opened Jun 16, 2026 by
JohnQinAMD
Loading…
[codex] Add MiniMax M3 float32 matmul precision env
#553
opened Jun 15, 2026 by
jasonlizhengjian
•
Draft
[ROCm] Enable FlyDSL w4a16 MoE for Kimi INT4
#552
opened Jun 15, 2026 by
amd-asalykov
Contributor
•
Draft
Update Kimi-K2 Thinking AMD recipe YAML format
#549
opened Jun 15, 2026 by
haic0
Contributor
Loading…
Update DeepSeek-V3.2-Exp AMD recipe YAML format
#546
opened Jun 15, 2026 by
haic0
Contributor
Loading…
Update DeepSeek V3 and R1 AMD recipe YAML format
#545
opened Jun 15, 2026 by
haic0
Contributor
Loading…
Update Nemotron 3 Nano AMD recipe YAML format
#532
opened Jun 12, 2026 by
haic0
Contributor
Loading…
Add LB support with distributed and centralized KV cache storage strategy configuration
#500
opened Jun 1, 2026 by
mpashkovskii
Loading…
Previous Next
ProTip!
no:milestone will show everything without a milestone.