-
Notifications
You must be signed in to change notification settings - Fork 330
Pull requests: vllm-project/recipes
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Update the Qwen3.6-27B DGX Spark guide with tuned arguments
#647
opened Jul 16, 2026 by
prodney-dev
Loading…
Update the Qwen3.6-35B-A3B-NVFP4 DGX Spark guide with tuned arguments
#643
opened Jul 16, 2026 by
prodney-dev
Loading…
Add ThaiLLM/ThaiLLM-30B recipe (first Thai/SEA model, DGX Spark verified NVFP4)
#640
opened Jul 15, 2026 by
spped2000
Loading…
Generalize Nemotron-3-Super DGX Spark config and document tuned command
#637
opened Jul 15, 2026 by
faradawn
Collaborator
Loading…
[AMD] MINIMAX-M3 vLLM Agentic Support.
#631
opened Jul 13, 2026 by
ajith-sirra-amd
Contributor
Loading…
Add MI355X MXFP4 + LMCache KV-offload to Kimi-K2.7-Code recipe
#630
opened Jul 13, 2026 by
hyukjlee
Loading…
docs: add DeepSeek V4 Pro DEP prefill scheduling
#629
opened Jul 12, 2026 by
xinli-sw
Contributor
Loading…
Update Kimi-K2.6 B300 NVFP4 recipe / 更新 Kimi-K2.6 B300 NVFP4 配置
#626
opened Jul 11, 2026 by
Ankur-singh
Contributor
Loading…
Document MiniMax-M3 index top-k reuse recipe
#621
opened Jul 8, 2026 by
tanpinsiang
Contributor
Loading…
chore: remove VLLM_USE_FLASHINFER_MOE_FP4 flag
#614
opened Jul 6, 2026 by
faradawn
Collaborator
Loading…
[ROCm] update MiniMax-M3 bf16 recipe on docker image and fp8_per_chanel quantization notes
#598
opened Jun 29, 2026 by
hongxiayang
Contributor
Loading…
Previous Next
ProTip!
Follow long discussions with comments:>50.