-
Notifications
You must be signed in to change notification settings - Fork 172
Pull requests: SemiAnalysisAI/InferenceX
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[AMD][ROCM] dsv4-fp4-mi355x-vllm, Bump vLLM ROCm image to (nightly-4f940896)
AMD
full-sweep-enabled
#1546
opened May 21, 2026 by
seungrokj
Collaborator
Loading…
1 task
[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 GB300 DSV4 Dynamo vLLM MTP recipes
full-sweep-enabled
#1535
opened May 20, 2026 by
hjjq
Collaborator
Loading…
dsr1-sglang: extend low-conc sweep to include conc=1 and conc=2
full-sweep-enabled
#1534
opened May 20, 2026 by
Ankur-singh
Collaborator
Loading…
gpt-oss-fp4-mi355x: pin to v0.19 + switch to AITER-env-based recipe
full-sweep-enabled
#1531
opened May 20, 2026 by
xiaohuguo2023
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…
Restore dpskv4 GB300 non-MTP disagg to staging image + deepep backend
full-sweep-enabled
#1526
opened May 20, 2026 by
yhyang201
Collaborator
Loading…
[WIP][NV] add minimax fp4 h100 vllm
full-sweep-enabled
#1517
opened May 19, 2026 by
hshrivastava-droid
Collaborator
Loading…
[WIP][NV] update Minimax2.5 fp8 h100 vllm
full-sweep-enabled
#1516
opened May 19, 2026 by
hshrivastava-droid
Collaborator
Loading…
Add GLM-5 FP4 GB300 dynamo-sglang disagg config
full-sweep-enabled
#1514
opened May 19, 2026 by
Ankur-singh
Collaborator
Loading…
dsv4-fp4-b300-sglang: update image to nightly
full-sweep-enabled
#1506
opened May 18, 2026 by
yhyang201
Collaborator
Loading…
run-sweep: gate full-sweep PRs behind a sequential canary
#1503
opened May 18, 2026 by
Oseltamivir
Collaborator
Loading…
3 tasks
[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
[Handoff to @Oseltamivir Claude /loop] [Klaud Cold] Add qwen3.5-fp8-mi300x-sglang-mtp recipe
full-sweep-enabled
#1482
opened May 18, 2026 by
functionstackx
Collaborator
Loading…
1 of 2 tasks
Update dpskv4 GB300 MTP disagg SGLang image to nightly-20260519
full-sweep-enabled
#1478
opened May 18, 2026 by
yhyang201
Collaborator
Loading…
[Handoff to @Oseltamivir Claude /loop] [Klaud Cold] Update dsv4-fp8-h200-vllm (+mtp) vLLM image to v0.21.0
full-sweep-enabled
#1461
opened May 17, 2026 by
functionstackx
Collaborator
Loading…
1 task
[Handoff to @Oseltamivir Claude /loop] [Klaud Cold] Update dsv4-fp8-h200-sglang (+mtp) SGLang image to v0.5.12-cu130
full-sweep-enabled
#1460
opened May 17, 2026 by
functionstackx
Collaborator
Loading…
1 task
[Handoff to @Oseltamivir Claude /loop] [Klaud Cold] Update dsv4-fp4-b300-sglang (+mtp) SGLang image to v0.5.12-cu130
full-sweep-enabled
#1455
opened May 17, 2026 by
functionstackx
Collaborator
Loading…
1 task
[Handoff to @Oseltamivir Claude /loop] [Klaud Cold] Update qwen3.5-fp8-b300-sglang (+mtp) SGLang image to v0.5.12-cu130
full-sweep-enabled
#1451
opened May 17, 2026 by
functionstackx
Collaborator
Loading…
1 task
[Handoff to @Oseltamivir Claude /loop] [Klaud Cold] Update dsv4-fp4-b200-sglang SGLang image to v0.5.12-cu130
full-sweep-enabled
#1450
opened May 17, 2026 by
functionstackx
Collaborator
Loading…
1 task
Previous Next
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.