Skip to content

Pull requests: NVIDIA/srt-slurm

New pull request New
21 Open 96 Closed
21 Open 96 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

recipes: add DeepSeek-V4 GB200 decode/prefill bench yamls
#124 opened Apr 30, 2026 by esmeetu Loading…
4 tasks
2
feat: live in-flight batch-metrics snapshotter (opt-in)
#115 opened Apr 29, 2026 by YAMY1234 Collaborator • Draft
1 of 3 tasks
2
multi process tokenizer in benchmark_serving
#114 opened Apr 29, 2026 by fzyzcjy Loading…
1
feat(vllm): update DP+EP to use --local-data-parallel-rank
#112 opened Apr 28, 2026 by njhill • Draft
feat: add vLLM GB200 GSM8K repro configs
#106 opened Apr 28, 2026 by alec-flowers Collaborator • Draft
feat(vllm): vllm gb200 dsv4 recipes
#103 opened Apr 28, 2026 by alec-flowers Collaborator • Draft
refactor(gpqa): drop structured runner; ship configs/gpqa/run.sh
#96 opened Apr 27, 2026 by ishandhanani Collaborator Loading…
1 of 2 tasks
1
feat: peak gen throughput metric in sa-bench + server-side node metrics CSV export
#93 opened Apr 27, 2026 by zhengd-nv Loading…
2
feat(vllm): switch DP+EP launch to hybrid_lb (per-node process)
#90 opened Apr 27, 2026 by esmeetu • Draft
Support vLLM DP ranks with tensor-parallel GPU groups
#86 opened Apr 27, 2026 by nealvaidya Loading…
1
GB300 DSv4 042626
#84 opened Apr 26, 2026 by ywang96 Loading…
Add DeepSeek V4 GB200 recipes
#77 opened Apr 25, 2026 by alec-flowers Collaborator Loading…
feat: use pre-generated custom dataset for benchmarking MTP with chat template
#63 opened Apr 23, 2026 by richardhuo-nv Collaborator Loading…
feat: SGLang decode slow_down for PD disagg nsys profiling (with skip-warmup workflow)
#60 opened Apr 23, 2026 by zhengd-nv Loading…
1
feat(profiling): add extra_nsys_args for optional nsys CLI flags
#59 opened Apr 23, 2026 by zhengd-nv Loading…
1
[codex] Add asset materialization POC
#57 opened Apr 21, 2026 by ishandhanani Collaborator Loading…
Add GLM5 B200 FP8 disaggregated recipe
#50 opened Apr 21, 2026 by weireweire Collaborator Loading…
1
Add lm-eval benchmark runner for evals
#41 opened Apr 17, 2026 by Oseltamivir Contributor Loading…
1
Built-in GPU performance monitoring during benchmarks
#35 opened Apr 13, 2026 by KaunilD Collaborator Loading…
1 of 3 tasks
2
Enable nsys profiling for vLLM
#28 opened Apr 10, 2026 by leo-cf-tian Contributor Loading…
4
[vllm] allow multiple DP workers per node
#10 opened Apr 6, 2026 by jasonlizhengjian • Draft
ProTip! Follow long discussions with comments:>50.