-
Notifications
You must be signed in to change notification settings - Fork 194
Pull requests: SemiAnalysisAI/InferenceX
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Klaud Cold][NVIDIA] feat: MiniMax M3 Day 0 support H200
full-sweep-enabled
#1728
opened Jun 12, 2026 by
functionstackx
Collaborator
Loading…
feat(ci): canary-gate full-sweep-fail-fast and add a no-canary variant
full-sweep-fail-fast
#1727
opened Jun 12, 2026 by
cquil11
Collaborator
Loading…
feat(ci): add priority label to preempt runners for high-priority sweeps
#1726
opened Jun 12, 2026 by
cquil11
Collaborator
Loading…
[NVIDIA] feat: MiniMax M3 Day 0 support B300
full-sweep-fail-fast
#1724
opened Jun 12, 2026 by
cquil11
Collaborator
Loading…
[NVIDIA] feat: MiniMax M3 Day 0 support B200
full-sweep-fail-fast
#1723
opened Jun 12, 2026 by
cquil11
Collaborator
Loading…
[WIP][NV] add minimaxm2.5-fp4-b200-trt
full-sweep-enabled
#1722
opened Jun 12, 2026 by
hshrivastava-droid
Collaborator
Loading…
Per-model gsm8k eval thresholds derived from IQR analysis
#1721
opened Jun 12, 2026 by
Oseltamivir
Collaborator
Loading…
5 tasks
[AMD] dsv4-fp4-mi355x-atom: enable DPA TBO at high concurrency, update image to atom0.1.4
AMD
full-sweep-enabled
#1717
opened Jun 12, 2026 by
seungrokj
Collaborator
Loading…
2 tasks
[AMD][MI35X] Qwen3.5-fp4 SGLang single-node benchmark env update
AMD
full-sweep-enabled
#1716
opened Jun 12, 2026 by
yichiche
Collaborator
Loading…
[AMD] remove accuracy wrong sweep point, bump image to sglang-rocm 20260609
AMD
full-sweep-enabled
#1714
opened Jun 12, 2026 by
billishyahao
Collaborator
Loading…
Add qwen3.5-fp4-b200-trt single-node TensorRT-LLM benchmark
full-sweep-enabled
#1711
opened Jun 11, 2026 by
RohitNagraj
Collaborator
Loading…
[DNM][AMD] job.slurm: add RDMA library version consistency check across all nodes
#1710
opened Jun 11, 2026 by
seungrokj
Collaborator
Loading…
2 tasks
[DNM][AMD] agentx-v0.4 rebased from commit chore/agentx-v0.4 commit 7f61
#1709
opened Jun 11, 2026 by
seungrokj
Collaborator
Loading…
2 tasks
[Klaud Cold] dsv4-fp4-mi355x-sglang-disagg: DeepSeek-V4-Pro SGLang disagg (8k1k conc=1 smoke test)
full-sweep-enabled
#1708
opened Jun 11, 2026 by
functionstackx
Collaborator
Loading…
5 tasks
[Klaud Cold] dsv4-fp4-mi355x-vllm-disagg: DeepSeek-V4-Pro vLLM disagg (8k1k conc=1 smoke test)
full-sweep-enabled
#1707
opened Jun 11, 2026 by
functionstackx
Collaborator
Loading…
4 tasks
[WIP] [NV] Update MiniMax B200/B300 aggregate vLLM settings
full-sweep-enabled
#1704
opened Jun 10, 2026 by
jasonlizhengjian
Collaborator
Loading…
dsv4-fp4-b300-sglang-mtp: add piecewise cuda graph flags
full-sweep-enabled
#1702
opened Jun 10, 2026 by
yhyang201
Collaborator
Loading…
[Do Not Merge] kimik2.5-fp4-b300-vllm: align server launch with B200 recipe
full-sweep-enabled
#1698
opened Jun 9, 2026 by
RohitNagraj
Collaborator
Loading…
[WIP][NV] add dsv4-fp4-gb300-dynamo-sglang-mtp-1k1k
full-sweep-enabled
#1697
opened Jun 9, 2026 by
hshrivastava-droid
Collaborator
Loading…
dsr1 disagg 8k1k mtp: nightly 20260609 + conc-64 dispatch-bug validation
non-canary-full-sweep-enabled
Run the full sweep without the canary gate (full search space, no trim)
#1696
opened Jun 9, 2026 by
Oseltamivir
Collaborator
Loading…
dsv4-fp4-b300-sglang: enable piecewise cuda graph and mixed chunk
full-sweep-enabled
#1693
opened Jun 9, 2026 by
yhyang201
Collaborator
Loading…
Previous Next
ProTip!
Updated in the last three days: updated:>2026-06-09.