-
Notifications
You must be signed in to change notification settings - Fork 230
Pull requests: SemiAnalysisAI/InferenceX
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Add GLM-5.2 full-context H200 AgentX with SGLang PCP and HiCache / 新增 GLM-5.2 H200 全上下文 AgentX SGLang PCP 与 HiCache 配置
#2275
opened Jul 18, 2026 by
JordanNanos
Collaborator
•
Draft
6 of 10 tasks
Add DeepSeek V4 GB300 Dynamo TensorRT-LLM agentic config / 添加 DeepSeek V4 GB300 Dynamo TensorRT-LLM Agentic 配置
full-sweep-enabled
#2274
opened Jul 18, 2026 by
Ankur-singh
Collaborator
Loading…
feat(agentic): add GLM-5.2 MI325X full-context sweeps / 新增 GLM-5.2 MI325X 全上下文 AgentX 扫描
#2273
opened Jul 18, 2026 by
JordanNanos
Collaborator
Loading…
Add GLM-5.2 FP8 MI355X SGLang single-node agentic benchmarks
full-sweep-fail-fast
#2272
opened Jul 18, 2026 by
Oseltamivir
Collaborator
Loading…
docs: add /ci-queue-times command for per-cluster CI queue latency / 新增 /ci-queue-times 命令：按集群查看 CI 排队延迟
#2270
opened Jul 18, 2026 by
JordanNanos
Collaborator
Loading…
3 of 9 tasks
[AgentX] vLLM DeepSeek-V4 GB300 disagg
full-sweep-enabled
#2269
opened Jul 18, 2026 by
ivanium
Collaborator
Loading…
[AMD][MI355X] Update Kimi K2.5 FP4 vLLM recipe
#2266
opened Jul 18, 2026 by
YukioZzz
Collaborator
Loading…
[AMD][MI35X] Qwen3.5-fp4 SGLang single-node benchmark env update
full-sweep-fail-fast
#2265
opened Jul 18, 2026 by
yichiche
Collaborator
Loading…
Add curated-full-sweep matching dashboard chart runs (two active tabs) / 新增匹配仪表盘图表的 curated-full-sweep（两个活跃标签页）
#2261
opened Jul 17, 2026 by
JordanNanos
Collaborator
Loading…
[AgentX] vLLM DeepSeek-V4 GB200 disagg
full-sweep-enabled
#2260
opened Jul 17, 2026 by
ivanium
Collaborator
Loading…
[AgentX] vLLM DeepSeek-V4 B200 aggregate MTP
full-sweep-enabled
#2259
opened Jul 17, 2026 by
majunze2001
Collaborator
Loading…
[AgentX] vLLM DeepSeek-V4 B300 aggregate MTP
full-sweep-enabled
#2258
opened Jul 17, 2026 by
majunze2001
Collaborator
Loading…
[AMD][dsv4] fix 2P1D 8k1k straggler (decode/prefill context-length asymmetry)
#2257
opened Jul 17, 2026 by
inkcherry
Loading…
[AMD][dsv4] fix 2P1D eval 503 "all circuits open" (readiness canary + faster CB recovery)
#2255
opened Jul 17, 2026 by
inkcherry
Loading…
[AMD][MI355X] Add DSv4 FP4 agentic MTP recipe with DPA tuning
agentx
AgentX benchmarks, recipes, and infrastructure
AMD
evals-only
Suppress throughput and run only eval jobs; combine with all-evals to expand selection
full-sweep-enabled
#2254
opened Jul 17, 2026 by
seungrokj
Collaborator
Loading…
3 tasks
Add DSV4 FP4 B200 disaggregated Dynamo SGLang MTP configuration / 新增 DSV4 FP4 B200 分离式 Dynamo SGLang MTP 配置
full-sweep-enabled
#2252
opened Jul 16, 2026 by
RohitNagraj
Collaborator
Loading…
Add DSV4 FP4 B200 Dynamo SGLang configuration / 新增 DSV4 FP4 B200 Dynamo SGLang 配置
full-sweep-enabled
#2251
opened Jul 16, 2026 by
RohitNagraj
Collaborator
Loading…
[NV] Kimi K2.5 NVFP4 B200 disaggregated TRT-LLM (Dynamo) recipe
full-sweep-enabled
#2249
opened Jul 16, 2026 by
richardhuo-nv
Collaborator
Loading…
[AMD] Optimize kimik2.5-fp4-mi355x-vllm-disagg: image bump + serve sync + all-TP4 P/D (EP off) / 优化 kimik2.5-fp4-mi355x-vllm-disagg：镜像升级 + serve 参数对齐 + 全 TP4 P/D（关闭 EP）
full-sweep-fail-fast
#2247
opened Jul 16, 2026 by
hongxiayang
Collaborator
Loading…
4 of 6 tasks
Qwen3.5 FP4 GB300 disagg dynamo-sglang: bump image to v0.5.14-cu130 + NVFP4-V2 checkpoint
full-sweep-enabled
#2238
opened Jul 16, 2026 by
hshrivastava-droid
Collaborator
Loading…
[LMCache] Add LMCache arm on tuned DSV4 FP4 B300 vLLM AgentX recipe / 在调优后的 DSV4 FP4 B300 vLLM AgentX 配方上新增 LMCache 分支
agentx
AgentX benchmarks, recipes, and infrastructure
full-sweep-enabled
#2232
opened Jul 16, 2026 by
ApostaC
Collaborator
Loading…
4 of 10 tasks
[LMCache] Add LMCache arm to official DSV4 FP4 B200 vLLM AgentX sweep / 将 LMCache 分支并入官方 DSV4 FP4 B200 vLLM AgentX 扫描
agentx
AgentX benchmarks, recipes, and infrastructure
full-sweep-enabled
#2231
opened Jul 16, 2026 by
ApostaC
Collaborator
Loading…
4 of 10 tasks
[WIP] feat(minimaxm3): add B200 disaggregated configs
full-sweep-enabled
#2230
opened Jul 15, 2026 by
xinli-sw
Collaborator
Loading…
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.