Skip to content

Pull requests: SemiAnalysisAI/InferenceX

New pull request New
70 Open 1,715 Closed
70 Open 1,715 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

chore(agentic): rerun DSV4 SGLang with standard warmup full-sweep-fail-fast
#2179 opened Jul 13, 2026 by cquil11 Collaborator • Draft
1
[AMD] Kimi-K2.5 MXFP4 ATOMESH disagg config AMD
#2172 opened Jul 13, 2026 by seungrokj Collaborator Loading…
3 tasks
8
[WIP] Add Kimi Agentic with LMCache NIXL agentx AgentX benchmarks, recipes, and infrastructure sweep-enabled
#2171 opened Jul 12, 2026 by YukioZzz Collaborator • Draft
4
[AMD][AgentX] DeepSeek-V4 MI355X agentic disaggregated benchmarking agentx AgentX benchmarks, recipes, and infrastructure AMD full-sweep-enabled
#2170 opened Jul 11, 2026 by ichbinblau Collaborator Loading…
19
Add Kimi K2.6 NVFP4 B300 EAGLE3 AgentX benchmark / 新增 Kimi K2.6 NVFP4 B300 EAGLE3 AgentX 基准测试 agentx AgentX benchmarks, recipes, and infrastructure full-sweep-enabled NVIDIA
#2158 opened Jul 10, 2026 by xinli-sw Collaborator Loading…
16
[WIP] Add GB300 DeepSeek-V4 dynamo-sglang agentic recipes agentx AgentX benchmarks, recipes, and infrastructure full-sweep-enabled NVIDIA
#2157 opened Jul 10, 2026 by csahithi Collaborator Loading…
33
[LMCache] Add LMCache configs for dsv4 vllm b200/b300 agentix setups agentx AgentX benchmarks, recipes, and infrastructure full-sweep-enabled
#2153 opened Jul 10, 2026 by ApostaC Collaborator Loading…
24
[WIP] Comparison branch for #2148: BF16 gate on main full-sweep-enabled NVIDIA
#2149 opened Jul 10, 2026 by jasonlizhengjian Collaborator Loading…
3
[WIP] MiniMax-M3 B300: use FlashInfer split-K nightly full-sweep-enabled NVIDIA
#2148 opened Jul 10, 2026 by jasonlizhengjian Collaborator Loading…
3
[AMD][MI355X] DSv4 SGLang agentic: v0.5.14 image, router, HiCache agentx AgentX benchmarks, recipes, and infrastructure AMD full-sweep-enabled
#2146 opened Jul 10, 2026 by seungrokj Collaborator Loading…
5 tasks
21
[Agentx][sglang] config update agentx AgentX benchmarks, recipes, and infrastructure full-sweep-enabled
#2145 opened Jul 10, 2026 by Oasis-Git Collaborator Loading…
8
fix: bump vllm-router image to nightly-20260708-b93cbcb / 升级 vllm-router 镜像至 nightly-20260708-b93cbcb
#2143 opened Jul 10, 2026 by hongxiayang Collaborator Loading…
2 tasks
2
Refresh DeepSeek-V4-Pro GB200 Dynamo vLLM stack / 更新 DeepSeek-V4-Pro GB200 Dynamo vLLM 推理栈 full-sweep-enabled
#2139 opened Jul 9, 2026 by Ankur-singh Collaborator Loading…
8
[AMD][AgentX] MINIMAX-M3 FP4 MI355X agentX vLLM agentx AgentX benchmarks, recipes, and infrastructure AMD full-sweep-enabled
#2129 opened Jul 9, 2026 by ajith-sirra-amd Collaborator • Draft
9
[AMD][AgentX] Kimi-K2.7-Code FP4 MI355X agentX vLLM agentx AgentX benchmarks, recipes, and infrastructure AMD full-sweep-enabled
#2126 opened Jul 9, 2026 by hyukjlee Collaborator Loading…
14
[WIP] Update vllm B300 Minimax M3 full-sweep-enabled NVIDIA
#2124 opened Jul 9, 2026 by jiahanc Collaborator Loading…
32
Add GLM-5.1 FP8 GB200 disaggregated dynamo-sglang MTP config / 添加 GLM-5.1 FP8 GB200 分离式 dynamo-sglang MTP 配置 full-sweep-enabled
#2123 opened Jul 9, 2026 by RohitNagraj Collaborator Loading…
4
GB200 DSv4 vLLM agentic full sweep (3p2d TEP8/TP8 + 2p1d DEP8/DEP8) agentx AgentX benchmarks, recipes, and infrastructure full-sweep-enabled
#2122 opened Jul 8, 2026 by cquil11 Collaborator Loading…
9
[NV] Add GB300 AgentX Qwen3.5 recipes agentx AgentX benchmarks, recipes, and infrastructure full-sweep-enabled NVIDIA
#2121 opened Jul 8, 2026 by csahithi Collaborator Loading…
19
[AMD][AgentX] MINIMAX-M3 FP4 MI355X agentX vLLM agentx AgentX benchmarks, recipes, and infrastructure AMD full-sweep-enabled
#2118 opened Jul 8, 2026 by ajith-sirra-amd Collaborator Loading…
31
[WIP] Test Kimi 2.5 B200 Agg agentx AgentX benchmarks, recipes, and infrastructure full-sweep-enabled NVIDIA
#2106 opened Jul 6, 2026 by wzhao18 Collaborator Loading…
12
[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
8
[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…
11
chore(config): backfill serving component metadata agentx AgentX benchmarks, recipes, and infrastructure
#2097 opened Jul 6, 2026 by cquil11 Collaborator • 2/2 Loading…
3
feat(config): separate P2P transfer and KV offload metadata agentx AgentX benchmarks, recipes, and infrastructure
#2096 opened Jul 6, 2026 by cquil11 Collaborator • 1/2 Loading…
5
ProTip! no:milestone will show everything without a milestone.