-
Notifications
You must be signed in to change notification settings - Fork 256
Pull requests: SemiAnalysisAI/InferenceX
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[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…
[CI] Add weekly overview snapshot sweep / [CI] 新增每周 overview snapshot 定时 sweep
#2588
opened Aug 13, 2026 by
edwingao28
Collaborator
Loading…
Kimi-K3 FP8 MI355X vLLM agentic recipe (base + DSpark MTP)
#2585
opened Aug 12, 2026 by
xiaohuguo2023
Collaborator
•
Draft
kimik3-fp4-mi355x-vllm-agentic-mtp: add LMCache DRAM KV-offload arm
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
full-sweep-enabled
#2583
opened Aug 12, 2026 by
sammshen
Collaborator
Loading…
[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…
[AMD][AgentX] Add MI300X MiniMax-M3 EAGLE3 MXFP8
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
full-sweep-enabled
#2580
opened Aug 12, 2026 by
cquil11
Collaborator
Loading…
Add MI300X GLM-5.2 FP8 AgentX MTP
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
full-sweep-enabled
#2581
opened Aug 12, 2026 by
cquil11
Collaborator
Loading…
[AMD] [AgentX] Add MiniMax-M3 MXFP8 EAGLE3 on MI325X
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
non-canary-full-sweep-enabled
Run the full sweep without the canary gate (full search space, no trim)
#2579
opened Aug 12, 2026 by
cquil11
Collaborator
Loading…
Refresh DeepSeek-V4 B300 SGLang AgentX MTP
full-sweep-enabled
#2577
opened Aug 12, 2026 by
cquil11
Collaborator
Loading…
Refresh DeepSeek-V4 B200 SGLang AgentX MTP
full-sweep-enabled
#2578
opened Aug 12, 2026 by
cquil11
Collaborator
Loading…
[AMD] [AGENTX] GLM-5.2 FP4 MI355X ATOM Agentic MTP
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
full-sweep-fail-fast
#2576
opened Aug 12, 2026 by
seungrokj
Collaborator
Loading…
2 tasks
[AgentX] Tune DSV4 GB300 MTP / 调优 DSV4 GB300 MTP
agentx
AgentX benchmarks, recipes, and infrastructure
full-sweep-enabled
#2571
opened Aug 12, 2026 by
ivanium
Collaborator
Loading…
Fix Kimi K3 B200 AIPerf metrics configuration
full-sweep-enabled
#2569
opened Aug 12, 2026 by
cquil11
Collaborator
Loading…
perf: add GB200 DeepSeek V4 FP4 vLLM MTP AgentX
full-sweep-enabled
#2567
opened Aug 11, 2026 by
cquil11
Collaborator
Loading…
chore(agentx): sync support with production results
#2561
opened Aug 11, 2026 by
cquil11
Collaborator
Loading…
Add DSV4 B200 disaggregated Dynamo SGLang STP configuration / 新增 DSV4 B200 分离式 Dynamo SGLang STP 配置
full-sweep-enabled
#2560
opened Aug 11, 2026 by
RohitNagraj
Collaborator
Loading…
4 of 9 tasks
feat: validate ATOM and Infera on MI300X and MI355X
#2558
opened Aug 11, 2026 by
cquil11
Collaborator
Loading…
[AMD] Qwen3.5-FP8 MI355X SGLang disagg perf tuning: image bump to v0.5.16, TP4P+TP8D baseline, add MTP / Qwen3.5-FP8 MI355X SGLang disagg 性能调优：镜像升级至v0.5.16，TP4P+TP8D基线优化，新增MTP配置
full-sweep-enabled
#2557
opened Aug 11, 2026 by
ChangLiu0709
Collaborator
Loading…
[AMD][AgentX] Port MI355X DeepSeek V4 MTP disagg to srt-slurm
full-sweep-enabled
#2555
opened Aug 11, 2026 by
cquil11
Collaborator
Loading…
Add DeepSeek-V4-Pro FP4 B200 Dynamo TensorRT-LLM recipes / 添加 DeepSeek-V4-Pro FP4 B200 Dynamo TensorRT-LLM 配置
full-sweep-enabled
#2552
opened Aug 10, 2026 by
RohitNagraj
Collaborator
Loading…
[AMD] Add kimik3-fp4-mi355x-vllm-agentic-dspark (AgentX, conc 1/2/4/8)
full-sweep-fail-fast
#2551
opened Aug 10, 2026 by
Fangzhou-Ai
Collaborator
•
Draft
3 tasks
Validate vLLM Router on GB200: DEP4, DEP8, and 1P/2D
agentx-fast
Run AgentX throughput with 1 warmup request per lane and a 20-minute profile; not reusable
full-sweep-enabled
#2549
opened Aug 10, 2026 by
cquil11
Collaborator
Loading…
Add pinned Kimi Vendor Verifier smoke / 添加固定版本的 Kimi Vendor Verifier 冒烟评估
full-sweep-fail-fast
#2547
opened Aug 10, 2026 by
adibarra
Collaborator
Loading…
Previous Next
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.