-
Notifications
You must be signed in to change notification settings - Fork 176
Pull requests: SemiAnalysisAI/InferenceX
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[AMD][MI35X]: add qwen3.5-fp4 MI355X SGLang PD-disaggregation
#1579
opened May 28, 2026 by
YukioZzz
Collaborator
Loading…
feat(power): per-worker prefill/decode power + role-split joules (stacked on #1574)
#1577
opened May 28, 2026 by
arygupt
Collaborator
Loading…
1 of 3 tasks
[NV] Update B300 DSV4 SGLang Pareto sweep
full-sweep-enabled
#1575
opened May 27, 2026 by
Ankur-singh
Collaborator
Loading…
feat(power): multinode measured-power aggregation
sweep-enabled
#1574
opened May 27, 2026 by
arygupt
Collaborator
Loading…
3 of 6 tasks
[MoRI short term temp patch] GLM-5 FP8 MI355X SGLang disaggregated
non-canary-full-sweep-enabled
Run the full sweep without the canary gate (full search space, no trim)
#1572
opened May 27, 2026 by
ChangLiu0709
Collaborator
Loading…
4 tasks
Update glm-5 b200 sglang image to nightly-dev-cu13-20260523-c112f762
full-sweep-enabled
#1567
opened May 26, 2026 by
Ankur-singh
Collaborator
Loading…
[AMD] feat(agentic): AgentX v0.3 — Kimi MI355X LMCache MP benchmark
#1565
opened May 26, 2026 by
seungrokj
Collaborator
Loading…
Update glm-5 container to use SGLang latest
full-sweep-enabled
NVIDIA
#1561
opened May 24, 2026 by
xinli-sw
Loading…
Yeswanth/minimax fp4 gb300 b300 dynamo vllm disagg
full-sweep-enabled
#1560
opened May 23, 2026 by
yeswanthk-26
Collaborator
Loading…
Add GLM5 FP8 dynamo-sglang GB300 disagg configs
#1557
opened May 22, 2026 by
yeswanthk-26
Collaborator
Loading…
[NV] Update B300 DSV4 SGLang Pareto sweep
full-sweep-enabled
#1552
opened May 22, 2026 by
YAMY1234
Loading…
[Klaud Cold] minimaxm2.5-fp8-mi300x: add SHUFFLE_KV_CACHE_LAYOUT=1 + ROCM_AITER_FA backend
full-sweep-enabled
#1550
opened May 21, 2026 by
functionstackx
Collaborator
Loading…
1 task
[Klaud Cold] minimaxm2.5-fp8-mi325x: add SHUFFLE_KV_CACHE_LAYOUT=1 + ROCM_AITER_FA backend
full-sweep-enabled
#1549
opened May 21, 2026 by
functionstackx
Collaborator
Loading…
1 task
[codex] fix profile relay and add B300 DSv4 Flash profile config
#1547
opened May 21, 2026 by
Oseltamivir
Collaborator
•
Draft
[NV] Update H100 Qwen3.5 SGLang agg config
full-sweep-enabled
NVIDIA
#1544
opened May 21, 2026 by
anish-shanbhag
Collaborator
Loading…
[NV] B300 (Agg): migrate model path
sweep-enabled
#1539
opened May 20, 2026 by
Ankur-singh
Collaborator
Loading…
[NV] H100 (Agg): migrate model path
sweep-enabled
#1537
opened May 20, 2026 by
Ankur-singh
Collaborator
Loading…
Add DSV4 GB300 1k1k STP disagg configs
full-sweep-enabled
#1530
opened May 20, 2026 by
yhyang201
Collaborator
Loading…
Update DSV4 GB300 8k1k MTP disagg configs
full-sweep-enabled
#1529
opened May 20, 2026 by
yhyang201
Collaborator
Loading…
dsv4-fp4-b300-sglang: update image to nightly
full-sweep-enabled
#1506
opened May 18, 2026 by
yhyang201
Collaborator
Loading…
[Handoff to @Oseltamivir Claude /loop] [Klaud Cold] Add dsr1-fp8-mi300x-sglang-mtp recipe
full-sweep-enabled
#1499
opened May 18, 2026 by
functionstackx
Collaborator
Loading…
1 of 2 tasks
[Handoff to @Oseltamivir Claude /loop] [Klaud Cold] Add glm5.1-fp4-mi355x-sglang-mtp recipe
full-sweep-enabled
#1494
opened May 18, 2026 by
functionstackx
Collaborator
Loading…
1 of 2 tasks
[Klaud Cold] Add glm5-fp8-mi300x-sglang (off + mtp) recipes
full-sweep-enabled
#1486
opened May 18, 2026 by
functionstackx
Collaborator
Loading…
1 of 2 tasks
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.