-
Notifications
You must be signed in to change notification settings - Fork 292
Pull requests: SemiAnalysisAI/InferenceX
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[AMD] [AGENTX] KIMI Perf Tuning
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
full-sweep-enabled
#3059
opened Sep 12, 2026 by
ajith-sirra-amd
Collaborator
Loading…
perf: MI355X DSv4.1 Flash on the ROCm nightly image with the CK a8w4 MoE experts / MI355X DSv4.1 Flash 切换 ROCm nightly 镜像并选择 CK a8w4 MoE 专家内核
full-sweep-enabled
#3058
opened Sep 12, 2026 by
Fangzhou-Ai
Collaborator
Loading…
[PowerX] collect native TileRT 8k1k power / 采集 TileRT 8k1k 原生功耗
#3057
opened Sep 12, 2026 by
edwingao28
Collaborator
Loading…
7 of 9 tasks
[PowerX] collect native llm-d 8k1k power / 采集 llm-d 8k1k 原生功耗
#3056
opened Sep 12, 2026 by
edwingao28
Collaborator
Loading…
7 of 9 tasks
[PowerX] isolate AMD monitor windows and worker lifecycle / 隔离 AMD 监控窗口与工作节点生命周期
#3055
opened Sep 12, 2026 by
edwingao28
Collaborator
Loading…
5 of 9 tasks
[AgentX H200] enable Kimi-K3 simple power / 启用 simple 实测功耗
#3054
opened Sep 12, 2026 by
edwingao28
Collaborator
Loading…
5 of 9 tasks
[AgentX H200] enable Kimi-K3 balanced power / 启用 balanced 实测功耗
#3053
opened Sep 12, 2026 by
edwingao28
Collaborator
Loading…
5 of 9 tasks
[PowerX] verify Slurm completion and normal llm-d exits / 验证 Slurm 完成与 llm-d 正常退出
#3052
opened Sep 12, 2026 by
edwingao28
Collaborator
Loading…
5 of 9 tasks
[PowerX] separate native multinode collector contract / 拆分原生多节点采集契约
#3051
opened Sep 12, 2026 by
edwingao28
Collaborator
Loading…
5 of 9 tasks
[PowerX] scope required power to selected 8k1k scenarios / 按所选 8k1k 场景要求功耗
#3050
opened Sep 12, 2026 by
edwingao28
Collaborator
Loading…
4 of 9 tasks
[AgentX GB300] enable Kimi-K3 disaggregated power / 启用分离部署功耗
#3047
opened Sep 12, 2026 by
edwingao28
Collaborator
Loading…
7 of 9 tasks
[AgentX GB300] enable Kimi-K3 aggregate power / 启用聚合部署功耗
#3046
opened Sep 12, 2026 by
edwingao28
Collaborator
Loading…
6 of 9 tasks
[AgentX GB200] enable Kimi-K3 aggregate power / 启用聚合部署功耗
#3045
opened Sep 12, 2026 by
edwingao28
Collaborator
Loading…
6 of 9 tasks
[AgentX H200] enable Kimi-K3 latency power / 启用 latency 实测功耗
#3044
opened Sep 12, 2026 by
edwingao28
Collaborator
Loading…
7 of 9 tasks
[AgentX B300] recover Kimi-K3 image and draft storage / 恢复镜像与草稿存储
#3040
opened Sep 12, 2026 by
edwingao28
Collaborator
Loading…
6 of 9 tasks
Add B200 DeepSeek V4.1 Flash P/D without KV offload / 新增无 KV 卸载的 B200 P/D
full-sweep-fail-fast
#3039
opened Sep 12, 2026 by
Oseltamivir
Collaborator
Loading…
Add B300 DeepSeek V4.1 Flash P/D without KV offload / 新增无 KV 卸载的 B300 P/D
full-sweep-fail-fast
#3038
opened Sep 12, 2026 by
Oseltamivir
Collaborator
Loading…
Add GB200 DeepSeek V4.1 Flash P/D without KV offload / 新增无 KV 卸载的 GB200 P/D
full-sweep-fail-fast
#3037
opened Sep 12, 2026 by
Oseltamivir
Collaborator
Loading…
Add GB300 DeepSeek V4.1 Flash P/D without KV offload / 新增无 KV 卸载的 GB300 P/D
full-sweep-fail-fast
#3036
opened Sep 12, 2026 by
Oseltamivir
Collaborator
Loading…
config: switch MI355X DSv4.1 Flash to the ROCm nightly image / MI355X DSv4.1 Flash 切换到 ROCm nightly 镜像
full-sweep-fail-fast
#3035
opened Sep 12, 2026 by
Fangzhou-Ai
Collaborator
Loading…
[DNM] Validate MI355X AITER + vLLM backend fixes / 联合验证 MI355X 后端修复
full-sweep-fail-fast
#3031
opened Sep 12, 2026 by
functionstackx
Collaborator
•
Draft
[PowerX] enable Kimi-K3 AgentX power backfills / 启用功耗补测
#3030
opened Sep 11, 2026 by
edwingao28
Collaborator
•
Draft
7 of 9 tasks
[Klaud Cold] Try TEP4 and DEP4 for DeepSeek V4.1 Flash AgentX on B300 / 在 B300 上尝试 DeepSeek V4.1 Flash AgentX 的 TEP4 与 DEP4
full-sweep-fail-fast
#3028
opened Sep 11, 2026 by
functionstackx
Collaborator
Loading…
[PowerX] support opt-in NVIDIA SRT 8k1k power / 支持按需启用 NVIDIA SRT 8k1k 功耗
#3027
opened Sep 11, 2026 by
edwingao28
Collaborator
Loading…
7 of 9 tasks
[PowerX] preserve request outcomes and incomplete batches / 保留请求结果与不完整批次
#3026
opened Sep 11, 2026 by
edwingao28
Collaborator
Loading…
5 of 9 tasks
Previous Next
ProTip!
Filter pull requests by the default branch with base:main.