-
Notifications
You must be signed in to change notification settings - Fork 284
Pull requests: SemiAnalysisAI/InferenceX
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix(speedbench-al): auto-PR commits golden AL matrix to golden_al_distribution/
#2847
opened Sep 6, 2026 by
connectors-testing-pplx
•
Draft
3 tasks done
fix: complete Klaud final sweep lifecycle / 完善 Klaud 最终扫描流程
#2843
opened Sep 5, 2026 by
adibarra
Collaborator
Loading…
[Klaud Cold] Update dsv4-fp4-mi355x-vllm-agentic-mtp vLLM ROCm image to nightly-e962733e08d10f7ca65dac4df99e116460b8b174
full-sweep-enabled
#2841
opened Sep 5, 2026 by
functionstackx
Collaborator
Loading…
1 task
perf(agentx): restore LMCache retrieves on Kimi-K3 MI355X DCP8
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
full-sweep-enabled
#2831
opened Sep 4, 2026 by
sammshen
Collaborator
Loading…
[Klaud Cold] glm5.2-fp4-b200-sglang-agentic-mtp: extend the AgentX curve to concurrency 48 with EP8/DEP8 arms / 以 EP8/DEP8 分支将 GLM-5.2 B200 SGLang AgentX 曲线扩展至并发度 48
full-sweep-fail-fast
#2828
opened Sep 4, 2026 by
functionstackx
Collaborator
Loading…
feat: add controlled AgentX power experiment / 添加受控 AgentX 功耗实验
#2827
opened Sep 4, 2026 by
edwingao28
Collaborator
Loading…
[AMD][DSV4] Disagg AgentX DP-attention tuning, HiCache ratio investigation, FP4 sparse-attention indexer
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
#2823
opened Sep 4, 2026 by
ichbinblau
Collaborator
Loading…
fix(agentx): refresh GB200 Dynamo-vLLM with complete DP metrics
full-sweep-enabled
#2822
opened Sep 4, 2026 by
cquil11
Collaborator
Loading…
Use DSpark6 for B200 DSV4 SGLang AgentX / B200 DSV4 SGLang AgentX 使用 DSpark6
full-sweep-enabled
#2821
opened Sep 4, 2026 by
nvpohanh
Collaborator
Loading…
CollectiveX: move to NCCL EP v0.2 and extend platform coverage
#2820
opened Sep 3, 2026 by
artpol84
Loading…
[wip - contains patches that need to be removed] [amd agentx m3 atom]
#2816
opened Sep 3, 2026 by
charxwu
Collaborator
Loading…
CollectiveX: NCCL EP v0.2 via nccl-extensions — lift the LL clamp, enable LL rows and B200 EP16
#2815
opened Sep 3, 2026 by
Oseltamivir
Collaborator
Loading…
Update Kimi K3 B300 AgentX / 更新 Kimi K3 B300 AgentX
full-sweep-enabled
#2814
opened Sep 3, 2026 by
mispa-ms
Collaborator
Loading…
perf(agentx): add Qwen3.5 GB300 SGLang Pareto curve / 性能：新增 Qwen3.5 GB300 SGLang Pareto 曲线
full-sweep-enabled
#2812
opened Sep 3, 2026 by
Ankur-singh
Collaborator
Loading…
config(minimaxm3): refresh full GB200 Dynamo-vLLM disaggregated curve / 刷新完整 GB200 Dynamo-vLLM 解耦曲线
full-sweep-enabled
#2807
opened Sep 2, 2026 by
RohitNagraj
Collaborator
Loading…
4 of 9 tasks
ci: use Fable 5.1 for all Claude Code invocations
#2805
opened Sep 2, 2026 by
cquil11
Collaborator
Loading…
perf(agentx): add LMCache offload arm to Kimi-K3 B300 at conc 56/70
ci-patchwork-waived
full-sweep-enabled
#2802
opened Sep 1, 2026 by
sammshen
Collaborator
Loading…
2 tasks
[AMD][MI35X] Enable fused allreduce+RMSNorm for Qwen3.5 MXFP4 MI355X agentic-mtp
full-sweep-enabled
#2801
opened Sep 1, 2026 by
ChangLiu0709
Collaborator
Loading…
Validate vLLM P/D cache-source metrics on GB300
full-sweep-enabled
#2797
opened Sep 1, 2026 by
cquil11
Collaborator
Loading…
Validate bounded vLLM cache token sources on H100
full-sweep-enabled
#2796
opened Sep 1, 2026 by
cquil11
Collaborator
Loading…
[AMD] [AGENTX] Kimi Perf Tuning
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
#2795
opened Sep 1, 2026 by
ajith-sirra-amd
Collaborator
Loading…
Previous Next
ProTip!
Adding no:label will show everything without a label.