Skip to content

Pull requests: SemiAnalysisAI/InferenceX

New pull request New
120 Open 2,143 Closed
120 Open 2,143 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[AMD] [AGENTX] Minimax-M3 Perf Tuning agentx AgentX benchmarks, recipes, and infrastructure AMD
#2671 opened Aug 19, 2026 by ajith-sirra-amd Collaborator Loading…
1
feat(agentx): add Kimi-K3 FP4 MI355X ATOM DSpark recipe
#2670 opened Aug 19, 2026 by zejunchen-zejun • Draft
Perf tuning for GB300 agentx Kimi K3 full-sweep-enabled
#2669 opened Aug 19, 2026 by wzhao18 Collaborator Loading…
1
[AMD][AgentX] Add DeepSeek-V4-Pro FP4 MI355X ATOM MTP / 新增 DeepSeek-V4-Pro ATOM MTP agentx AgentX benchmarks, recipes, and infrastructure AMD
#2668 opened Aug 19, 2026 by yhl-amd Loading…
1
docs(golden_al): document ATOM's forced acceptance-length setting agentx AgentX benchmarks, recipes, and infrastructure AMD
#2667 opened Aug 19, 2026 by whx-sjtu Loading…
feat(config): add GLM-5.2 B300 Dynamo-TRT AgentX MTP / 添加 GLM-5.2 B300 Dynamo-TRT AgentX MTP 配置 full-sweep-enabled
#2666 opened Aug 19, 2026 by RohitNagraj Collaborator Loading…
4 of 9 tasks
4
perf(gb300): refresh AgentX vLLM MTP P/D recipes / 刷新 GB300 AgentX vLLM MTP P/D 配方
#2665 opened Aug 19, 2026 by ivanium Collaborator • Draft
1
Add MiniMax-M3 NVFP4 GB300 vLLM Disaggregated AgentX with EAGLE3-GQA MTP / 新增 MiniMax-M3 NVFP4 GB300 vLLM 分离式 AgentX EAGLE3-GQA MTP 配置 full-sweep-fail-fast
#2663 opened Aug 18, 2026 by hshrivastava-droid Collaborator Loading…
4 of 6 tasks
5
Fix AgentX KV offload metadata
#2662 opened Aug 18, 2026 by cquil11 Collaborator • Draft
1
Refresh GB200 Qwen3.5 AgentX Pareto / 刷新 GB200 Qwen3.5 AgentX Pareto 配置 full-sweep-enabled
#2660 opened Aug 18, 2026 by Ankur-singh Collaborator Loading…
4 of 9 tasks
6
feat(config): add GLM-5.2 GB300 Dynamo-TRT AgentX / 添加 GLM-5.2 GB300 Dynamo-TRT AgentX 配置 full-sweep-enabled
#2657 opened Aug 18, 2026 by RohitNagraj Collaborator Loading…
8
[WIP] Add GLM-5.2-NVFP4 B300 AgentX recipes full-sweep-enabled NVIDIA
#2654 opened Aug 18, 2026 by csahithi Collaborator Loading…
7
Add Qwen3.5 FP4 B300 TRT-LLM Disaggregated AgentX / 新增 Qwen3.5 FP4 B300 TRT-LLM 分离式 AgentX full-sweep-enabled
#2653 opened Aug 18, 2026 by richardhuo-nv Collaborator Loading…
8
[NV][AgentX] Add glm5.1-fp8-b200-tilert-agentic (TileRT PD disagg) / [NV][AgentX] 新增 glm5.1-fp8-b200-tilert-agentic（TileRT PD 分离） full-sweep-fail-fast
#2650 opened Aug 18, 2026 by Oseltamivir Collaborator Loading…
11
perf(gb200): refresh AgentX vLLM MTP recipes / 刷新 GB200 AgentX vLLM MTP 配方 agentx AgentX benchmarks, recipes, and infrastructure full-sweep-enabled
#2648 opened Aug 18, 2026 by ivanium Collaborator Loading…
4
perf(agentx): refresh B300 vLLM MTP recipe / 刷新 B300 vLLM MTP 配置 agentx AgentX benchmarks, recipes, and infrastructure full-sweep-enabled
#2647 opened Aug 18, 2026 by ivanium Collaborator Loading…
5
perf(agentx): refresh B200 vLLM MTP recipe / 刷新 B200 vLLM MTP 配置 agentx AgentX benchmarks, recipes, and infrastructure full-sweep-enabled
#2646 opened Aug 18, 2026 by ivanium Collaborator Loading…
4
[NV][AgentX] Add glm5.1-fp8-b200-tilert-agentic (TileRT PD disagg) / [NV][AgentX] 新增 glm5.1-fp8-b200-tilert-agentic（TileRT PD 分离）
#2645 opened Aug 18, 2026 by CrimsonDump • Draft
4 of 5 tasks
Update DeepSeek-V4-Pro (DSV4) FP4 GB300 Dynamo-SGLang AgentX MTP configs / 更新 DeepSeek-V4-Pro（DSV4）FP4 GB300 Dynamo-SGLang AgentX MTP 配置 full-sweep-enabled NVIDIA
#2644 opened Aug 18, 2026 by weireweire Collaborator Loading…
4 of 9 tasks
5
AMD AgentX MI355X: GPU sanity dedup, HiCache tuning, node-exclude scoping, and DSv4 disagg image bump agentx AgentX benchmarks, recipes, and infrastructure AMD full-sweep-enabled
#2643 opened Aug 18, 2026 by ichbinblau Collaborator Loading…
3 tasks
7
feat(config): add GLM-5.2 FP4 GB200 SGLang AgentX MTP / 添加 GLM-5.2 FP4 GB200 SGLang AgentX MTP 配置 full-sweep-enabled
#2642 opened Aug 18, 2026 by RohitNagraj Collaborator Loading…
5 of 9 tasks
6
[AMD][MI35X] Bump Qwen3.5 MXFP4 MI355X SGLang single-node image to v0.5.17 full-sweep-fail-fast
#2640 opened Aug 18, 2026 by yichiche Collaborator Loading…
8
Kimi K3 vllm GB200 Agentx full-sweep-enabled
#2639 opened Aug 18, 2026 by wzhao18 Collaborator Loading…
13
Add lightweight tool-use verifier evaluations / 添加轻量级工具调用验证评估
#2634 opened Aug 17, 2026 by adibarra Collaborator • Draft
12 of 16 tasks
WIP: port MI355X DeepSeek-R1 MXFP4 disagg to srt-slurm full-sweep-enabled
#2633 opened Aug 17, 2026 by cquil11 Collaborator Loading…
5
ProTip! Follow long discussions with comments:>50.