Skip to content

Pull requests: NVIDIA/srt-slurm

New pull request New
62 Open 206 Closed
62 Open 206 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

Added b200 Kimi K2.6 vLLM fp4 recipes
#282 opened Jul 27, 2026 by RohitNagraj Loading…
1
Added b300 dsv4 sglang fp4 recipes
#281 opened Jul 27, 2026 by RohitNagraj Loading…
1
feat(vllm): support direct aggregate serving
#278 opened Jul 21, 2026 by kyleliang-nv Collaborator Loading…
feat(benchmark): expose logical worker endpoints
#276 opened Jul 21, 2026 by cquil11 Contributor Loading…
Add DSV4-Pro disagg frontier recipes (B200 + B300) on rc21 + Dynamo nightly
#274 opened Jul 20, 2026 by tanmayv25 Contributor Loading…
1
feat(vllm): default DP launch to per-node hybrid LB
#272 opened Jul 18, 2026 by alec-flowers Collaborator • Draft
1
feat(vllm): support mixed DP launch modes
#271 opened Jul 18, 2026 by esmeetu Contributor • Draft
Add fields for working GPU count in rollup data and use working GPU count to compute total_throughput_per_gpu
#270 opened Jul 17, 2026 by HuiGao-NV Loading…
2
Add srtctl partial-GPU placement knobs for MiniMax-M3 B200 disagg
#266 opened Jul 15, 2026 by xinli-sw Collaborator Loading…
feat(mooncake): manage standalone store services
#265 opened Jul 15, 2026 by 00fish0 Loading…
3
fix(profiling): use Dynamo control/ engine routes for start/stop_profile
#264 opened Jul 14, 2026 by shyeh25 Loading…
1
add B200 FP8 GLM5 sglang-dynamo disagg sweep configs
#262 opened Jul 13, 2026 by yeswanthk-26 Loading…
Add Kimi K2.5 1P1D AIPerf recipe
#257 opened Jul 10, 2026 by esmeetu Contributor • Draft
Run worker fingerprint capture from mounted script
#256 opened Jul 9, 2026 by alec-flowers Collaborator • Draft
1
Serialize hash-pinned dynamo install per node (fix concurrent pip race)
#245 opened Jul 6, 2026 by Ankur-singh Collaborator Loading…
fix(sa-bench): fix rollup key mapping for p99 latencies, token counts, and ISL/OSL
#241 opened Jul 4, 2026 by arpera Contributor Loading…
10
Added gb200 glm5 fp8 mtp recipes
#237 opened Jul 2, 2026 by nvjullin Contributor Loading…
1
Add gb200 glm5 fp4 mtp recipes
#230 opened Jun 24, 2026 by nvjullin Contributor Loading…
1
recipes: add vLLM DSV4-Pro agentic disagg references
#229 opened Jun 23, 2026 by esmeetu Contributor Loading…
2
Added gb200 glm5 fp8 1k1k/8k1k STP recipes
#221 opened Jun 15, 2026 by nvjullin Contributor Loading…
1
Add MiniMax-M2.7-NVFP4 disagg trtllm_dynamo recipes (GB300, 1K/1K)
#216 opened Jun 12, 2026 by tanmayv25 Contributor Loading…
1
Preserve sweep placeholder value types
#213 opened Jun 10, 2026 by fallintoplace Loading…
1
Apply default bash preamble without wrapper
#212 opened Jun 10, 2026 by fallintoplace Loading…
1
Add gb200 glm5 fp4 recipes
#211 opened Jun 10, 2026 by nvjullin Contributor Loading…
1
[WIP] ADd Kimi-K2.5 FP4 TRTLLM GB200/GB300 configs
#204 opened Jun 8, 2026 by xinli-sw Collaborator Loading…
ProTip! Mix and match filters to narrow down what you’re looking for.