-
Notifications
You must be signed in to change notification settings - Fork 155
Pull requests: SemiAnalysisAI/InferenceX
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[AMD/Hyperloom] Tune dsr1-fp8-mi355x-sglang: --num-continuous-decode-steps 4 → 8
sweep-enabled
#1243
opened May 1, 2026 by
lishuoshuo-amd
Collaborator
Loading…
4 tasks done
[NV] [DoNotMerge] Add DSV4-pro GB300 vLLM recipes
full-sweep-enabled
#1238
opened Apr 30, 2026 by
hjjq
Collaborator
Loading…
[AMD] Update MI355x Deepseek-R1 FP4 SGLang Image to v0.5.10
#1237
opened Apr 30, 2026 by
ppalanga
Collaborator
Loading…
[AMD][Waiting for switching upstream sglang image] improve dsr1 fp4 disagg perf on mi355x
#1236
opened Apr 30, 2026 by
billishyahao
Collaborator
Loading…
Adjust MiniMax MI355X block size for TP8 EP8
#1228
opened Apr 29, 2026 by
jiacao-amd
Collaborator
Loading…
Add DSv4 FP8 H200 vLLM MTP benchmark
full-sweep-enabled
#1222
opened Apr 29, 2026 by
functionstackx
Contributor
Loading…
4 tasks
chore: upstream srt-slurm recipes + first-class recipe field + custom-bench wrapper
#1211
opened Apr 28, 2026 by
cquil11
Collaborator
Loading…
[no merge] bump to nightly vllm and use vllm-router
#1208
opened Apr 28, 2026 by
simondanielsson
•
Draft
Add dsv4-fp4-b300-vllm-mtp config (DSv4 vLLM B300 + MTP)
sweep-enabled
#1203
opened Apr 28, 2026 by
Oseltamivir
Collaborator
Loading…
6 tasks
[disclaimer: MVP/experimental] feat: agentic trace replay benchmark MVP v0.1
#1201
opened Apr 27, 2026 by
cquil11
Collaborator
Loading…
Previous Next
ProTip!
Follow long discussions with comments:>50.