-
Notifications
You must be signed in to change notification settings - Fork 257
Pull requests: SemiAnalysisAI/InferenceX
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[AgentX] Mirror GB300 MTP tuning (#2571) to GB200 with 4-GPU->8-GPU workers
full-sweep-enabled
#2619
opened Aug 15, 2026 by
xinli-sw
Collaborator
Loading…
2 tasks
[wip][nv] k3 b200 dcp8
full-sweep-enabled
#2618
opened Aug 15, 2026 by
xinli-sw
Collaborator
Loading…
[AMD][AgentX] bring umbp L3 into dsv4 pro on MI355X
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
full-sweep-enabled
#2617
opened Aug 15, 2026 by
billishyahao
Collaborator
Loading…
fix(gb200): skip srtctl preflight on all paths / GB200：所有配方跳过 srtctl 预检
#2615
opened Aug 14, 2026 by
hshrivastava-droid
Collaborator
Loading…
Add Qwen3.5-397B-A17B-NVFP4-V2 GB300 TRT-LLM disaggregated AgentX
full-sweep-enabled
#2612
opened Aug 14, 2026 by
richardhuo-nv
Collaborator
Loading…
feat(minimaxm3): refresh B200 AgentX Pareto points with EAGLE3-GQA / 使用 EAGLE3-GQA 刷新 MiniMax-M3 B200 AgentX 帕累托点
full-sweep-enabled
#2611
opened Aug 14, 2026 by
xinli-sw
Collaborator
Loading…
6 tasks done
feat(minimaxm3): refresh B300 AgentX Pareto points with EAGLE3-GQA / 使用 EAGLE3-GQA 刷新 MiniMax-M3 B300 AgentX 帕累托点
full-sweep-enabled
#2610
opened Aug 14, 2026 by
xinli-sw
Collaborator
Loading…
6 tasks done
Add GLM-5.2-NVFP4 GB300 SGLang AgentX recipes / 新增 GLM-5.2-NVFP4 GB300 SGLang AgentX 配方
full-sweep-enabled
NVIDIA
#2608
opened Aug 14, 2026 by
csahithi
Collaborator
Loading…
7 of 8 tasks
[AMD] Qwen3.5-FP8 MI355X SGLang disagg MTP: EAGLE speculative decoding / Qwen3.5-FP8 MI355X SGLang disagg MTP：新增EAGLE投机解码配置
full-sweep-enabled
#2607
opened Aug 14, 2026 by
ChangLiu0709
Collaborator
Loading…
[AMD] Qwen3.5-FP8 MI355X SGLang disagg baseline: image bump to v0.5.16, TP4P+TP8D / Qwen3.5-FP8 MI355X SGLang disagg 基线优化：镜像升级至v0.5.16，TP4P+TP8D拓扑优化
full-sweep-enabled
#2606
opened Aug 14, 2026 by
ChangLiu0709
Collaborator
Loading…
[AMD] [AGENTX] Qwen3.5 FP4 MI355X SGLang Agentic MTP / Qwen3.5 FP4 MI355X SGLang Agentic 数据集 MTP 基准配置
#2605
opened Aug 14, 2026 by
ChangLiu0709
Collaborator
Loading…
[AMD] [AGENTX] Kimi-K3 Performance Tuning
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
full-sweep-enabled
#2602
opened Aug 14, 2026 by
ajith-sirra-amd
Collaborator
Loading…
[Power] feat: measure GPU power for single-node AgentX runs / 为单机 AgentX 运行接入 GPU 功耗测量
#2601
opened Aug 14, 2026 by
edwingao28
Collaborator
Loading…
[Power] feat: stamp whole-deployment semantics with a schema version / 为功耗指标加盖整机语义版本号
#2599
opened Aug 14, 2026 by
edwingao28
Collaborator
Loading…
kimik3-fp4-mi355x-vllm-agentic-mtp: add LMCache DRAM KV-offload arm
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
full-sweep-enabled
#2598
opened Aug 14, 2026 by
sammshen
Collaborator
Loading…
kimik3-fp4-b300-vllm-agentic-dspark: add LMCache DRAM KV-offload arm
agentx
AgentX benchmarks, recipes, and infrastructure
full-sweep-enabled
NVIDIA
#2597
opened Aug 14, 2026 by
sammshen
Collaborator
Loading…
Add DeepSeek-V4-Pro FP4 B300 Dynamo TensorRT-LLM recipes / 添加 DeepSeek-V4-Pro FP4 B300 Dynamo TensorRT-LLM 配方
full-sweep-enabled
#2596
opened Aug 14, 2026 by
RohitNagraj
Collaborator
Loading…
4 of 9 tasks
feat(dsv4): add GB300 Dynamo-TensorRT-LLM AgentX recipes / 添加 GB300 Dynamo-TensorRT-LLM AgentX 配置
full-sweep-enabled
#2595
opened Aug 13, 2026 by
RohitNagraj
Collaborator
Loading…
3 of 9 tasks
Add Qwen3.5 NVFP4 V2 GB200 Dynamo-SGLang MTP / 新增 Qwen3.5 NVFP4 V2 GB200 Dynamo-SGLang MTP 配置
#2594
opened Aug 13, 2026 by
RohitNagraj
Collaborator
Loading…
5 of 9 tasks
Add Qwen3.5 H200 MTP config / 新增 Qwen3.5 H200 MTP 配置
full-sweep-enabled
#2592
opened Aug 13, 2026 by
hshrivastava-droid
Collaborator
Loading…
3 of 9 tasks
[AMD][AgentX] support native ATOM server metrics
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
#2591
opened Aug 13, 2026 by
zhuyuhua-v
•
Draft
2 tasks done
[AMD] [AgentX] dsv4-fp4-mi355x-vllm-agentic-mtp, update image and extend the DP-attention concurrency curve
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
full-sweep-enabled
#2590
opened Aug 13, 2026 by
jiacao-amd
Collaborator
Loading…
Kimi-K3 FP8 MI355X vLLM agentic recipe (base + DSpark MTP)
#2585
opened Aug 12, 2026 by
xiaohuguo2023
Collaborator
•
Draft
[Klaud Cold] qwen3.5-fp4-mi355x-sglang-agentic-mtp: add HiCache DRAM offload arms / 为 MI355X Qwen3.5 FP4 SGLang AgentX MTP 新增 HiCache DRAM 卸载分支
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
full-sweep-enabled
#2582
opened Aug 12, 2026 by
functionstackx
Collaborator
Loading…
Previous Next
ProTip!
Adding no:label will show everything without a label.