-
Notifications
You must be signed in to change notification settings - Fork 222
Pull requests: SemiAnalysisAI/InferenceX
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[NV] llm-d: re-test max-tpt in-sweep with unique SLURM job-name fix
full-sweep-fail-fast
#2117
opened Jul 8, 2026 by
ezrasilvera
Collaborator
Loading…
Add GLM-5.1 NVFP4 GB200 disaggregated dynamo-sglang MTP config / 添加 GLM-5.1 NVFP4 GB200 分离式 dynamo-sglang MTP 配置
full-sweep-enabled
#2115
opened Jul 7, 2026 by
RohitNagraj
Collaborator
Loading…
Add GLM-5.1 NVFP4 GB300 disaggregated dynamo-sglang MTP config / 添加 GLM-5.1 NVFP4 GB300 分离式 dynamo-sglang MTP 配置
full-sweep-enabled
#2114
opened Jul 7, 2026 by
RohitNagraj
Collaborator
Loading…
Update DSR1 B200 FP4 dynamo-sglang MTP disagg sweep points
full-sweep-enabled
#2113
opened Jul 7, 2026 by
RohitNagraj
Collaborator
Loading…
dsv4 sglang agentic: enable out-of-window SWA slot release and bump image to nightly-20260707
#2112
opened Jul 7, 2026 by
cquil11
Collaborator
Loading…
[AMD] DSv4 MI355X agentX vLLM
AMD
full-sweep-enabled
#2109
opened Jul 7, 2026 by
seungrokj
Collaborator
Loading…
3 tasks
AMD][MI35X] 0706 DSV4 sglang mtp
AMD
full-sweep-fail-fast
#2108
opened Jul 7, 2026 by
1am9trash
Collaborator
Loading…
[WIP] Test Kimi 2.5 B200 Agg
full-sweep-enabled
#2106
opened Jul 6, 2026 by
wzhao18
Collaborator
Loading…
[AMD] MiniMax-M3 FP4 MI355X vLLM STP: INT4 all-reduce + fp8 KV, TP4 sweep / MiniMax-M3 FP4 MI355X vLLM STP：INT4 all-reduce + fp8 KV，TP4 扫描
full-sweep-fail-fast
#2104
opened Jul 6, 2026 by
Fangzhou-Ai
Collaborator
Loading…
3 tasks
[NV]Add DeepSeek-V4-Pro NVFP4 GB300 1k1k STP dynamo-sglang scenarios
full-sweep-enabled
#2099
opened Jul 6, 2026 by
hshrivastava-droid
Collaborator
Loading…
chore(config): backfill serving component metadata
#2097
opened Jul 6, 2026 by
cquil11
Collaborator
•
2/2
Loading…
feat(config): add router and KV transfer metadata
#2096
opened Jul 6, 2026 by
cquil11
Collaborator
•
1/2
Loading…
[AMD] Qwen3.5-FP8 MI355X SGLang disagg perf tuning: Docker image update / Qwen3.5-FP8 MI355X SGLang disagg 性能调优 更新Docker image
full-sweep-enabled
#2094
opened Jul 6, 2026 by
ChangLiu0709
Collaborator
Loading…
Add mooncake store for dsv4 and qwen35
non-canary-full-sweep-enabled
Run the full sweep without the canary gate (full search space, no trim)
#2089
opened Jul 6, 2026 by
Oseltamivir
Collaborator
Loading…
Single-node DSR1 FP8 sglang smoke on CoreWeave B300; prune matrix to dsr1-b300-cw + kimi multinode
sweep-enabled
#2086
opened Jul 5, 2026 by
JordanNanos
Collaborator
Loading…
[Klaud Cold] [AMD] gpt-oss-fp4-mi355x (vllm): W4A8 moe optimizations and vllm image bump / gpt-oss-fp4-mi355x（vLLM）：W4A8 MoE 优化与 vLLM 镜像升级
full-sweep-fail-fast
#2051
opened Jul 4, 2026 by
xiaohuguo2023
Collaborator
Loading…
[NV] llm-d-vllm: Add llm-d to the InferenceX benchmarking framework
full-sweep-enabled
#2050
opened Jul 4, 2026 by
ezrasilvera
Collaborator
Loading…
3 tasks
[AMD] MiniMax-M3 FP4/FP8 MI355X ATOMESH (disagg): (0701) refactor config
AMD
full-sweep-enabled
#2000
opened Jul 3, 2026 by
seungrokj
Collaborator
Loading…
8 tasks done
Previous Next
ProTip!
Adding no:label will show everything without a label.