Skip to content

Actions: sgl-project/sglang

Actions

PR Test (Xeon)

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pr-test-xeon.yml
8,430 workflow runs
8,430 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Support modelopt llama4 nvfp4 workflow and fix issues PR Test (Xeon) #11358: Pull request #9526 synchronize by zhyncs
August 29, 2025 01:41 5h 5m 26s Edwardf0t1:zhiyu/enable-modelopt-llama4-nvfp4
Edwardf0t1:zhiyu/enable-modelopt-llama4-nvfp4
August 29, 2025 01:41 5h 5m 26s
[feat] Add P/D attention select for draft model PR Test (Xeon) #11357: Pull request #9755 synchronize by zhyncs
August 29, 2025 01:36 Action required Ximingwang-09:pd_attention_select_for_draft
Ximingwang-09:pd_attention_select_for_draft
August 29, 2025 01:36 Action required
bugfix(hicache): Move exists check before key suffixing (#9749) PR Test (Xeon) #11356: Commit 38cd5fb pushed by zhyncs
August 29, 2025 01:29 3h 39m 0s main
main
August 29, 2025 01:29 3h 39m 0s
[HiCache] change the default policy to write through (#9772) PR Test (Xeon) #11355: Commit 001f519 pushed by zhyncs
August 29, 2025 01:28 59m 23s main
main
August 29, 2025 01:28 59m 23s
[NVIDIA] Optimize the silu_and_mul_scaled_fp4_grouped_quant perf PR Test (Xeon) #11354: Pull request #9556 synchronize by kaixih
August 29, 2025 01:15 3h 52m 46s kaixih:opt_quant_perf
kaixih:opt_quant_perf
August 29, 2025 01:15 3h 52m 46s
[NVIDIA] Optimize the silu_and_mul_scaled_fp4_grouped_quant perf PR Test (Xeon) #11353: Pull request #9556 synchronize by kaixih
August 29, 2025 01:12 3m 8s kaixih:opt_quant_perf
kaixih:opt_quant_perf
August 29, 2025 01:12 3m 8s
[NVIDIA] Optimize the silu_and_mul_scaled_fp4_grouped_quant perf PR Test (Xeon) #11352: Pull request #9556 synchronize by kaixih
August 29, 2025 01:08 1h 15m 57s kaixih:opt_quant_perf
kaixih:opt_quant_perf
August 29, 2025 01:08 1h 15m 57s
Optimized deepseek-v3/r1 model performance on mxfp4 run PR Test (Xeon) #11351: Pull request #9671 synchronize by kkHuang-amd
August 29, 2025 01:02 Action required HaiShaw:dsv3_opt_0822
HaiShaw:dsv3_opt_0822
August 29, 2025 01:02 Action required
Support Multi Process Tokenizer Manager , New PR (#6555) PR Test (Xeon) #11350: Pull request #8964 synchronize by whybeyoung
August 29, 2025 01:01 53m 0s whybeyoung:feature/multi_tokenizer_manager
whybeyoung:feature/multi_tokenizer_manager
August 29, 2025 01:01 53m 0s
[HiCache] resolve conflict between chunked-prefill and hicache hit count PR Test (Xeon) #11349: Pull request #9776 opened by xiezhq-hermann
August 29, 2025 00:50 1h 2m 20s xiezhq-hicache-chunk
xiezhq-hicache-chunk
August 29, 2025 00:50 1h 2m 20s
[Draft] replace ebnf with jsonschema for tool calls PR Test (Xeon) #11348: Pull request #9767 synchronize by TJ5
August 29, 2025 00:34 Action required TJ5:tool-call-jsonschema
TJ5:tool-call-jsonschema
August 29, 2025 00:34 Action required
Optimize prefill performance on cpu backend (#8750) PR Test (Xeon) #11347: Commit 5ad296b pushed by zhyncs
August 29, 2025 00:21 56m 41s main
main
August 29, 2025 00:21 56m 41s
Optimized deepseek-v3/r1 model performance on mxfp4 run PR Test (Xeon) #11346: Pull request #9671 synchronize by kkHuang-amd
August 29, 2025 00:16 Action required HaiShaw:dsv3_opt_0822
HaiShaw:dsv3_opt_0822
August 29, 2025 00:16 Action required
[MODEL] Apertus and XIELU PR Test (Xeon) #11345: Pull request #9774 synchronize by EduardDurech
August 29, 2025 00:10 2h 0m 30s swiss-ai:model/apertus
swiss-ai:model/apertus
August 29, 2025 00:10 2h 0m 30s
[Bug Fix] Resolve CUDA illegal memory access issue in speculative decoding PR Test (Xeon) #11344: Pull request #9687 synchronize by zhaochenyang20
August 29, 2025 00:09 37m 26s ryang-max:fix_eagle
ryang-max:fix_eagle
August 29, 2025 00:09 37m 26s
[Feature] Support custom set kv buffer kernel in srt PR Test (Xeon) #11343: Pull request #9775 opened by DarkSharpness
August 29, 2025 00:08 1h 9m 25s DarkSharpness:set_kv
DarkSharpness:set_kv
August 29, 2025 00:08 1h 9m 25s
feat: Add flexible validation for partial weight updates PR Test (Xeon) #11342: Pull request #9663 synchronize by zhaochenyang20
August 29, 2025 00:07 36m 21s GeLee-Q:fix_gpt_oss_update_weights
GeLee-Q:fix_gpt_oss_update_weights
August 29, 2025 00:07 36m 21s
[MODEL] Apertus and XIELU PR Test (Xeon) #11341: Pull request #9774 opened by EduardDurech
August 29, 2025 00:02 Action required swiss-ai:model/apertus
swiss-ai:model/apertus
August 29, 2025 00:02 Action required
Surface DeepGEMM commit in README.md PR Test (Xeon) #11340: Pull request #9773 opened by eicherseiji
August 28, 2025 23:40 Action required eicherseiji:improve-deepgemm-docs
eicherseiji:improve-deepgemm-docs
August 28, 2025 23:40 Action required
fix: fix MLA for ShardedModelLoader/RemoteModelLoader (#6287) PR Test (Xeon) #11339: Commit 9f81d74 pushed by zhyncs
August 28, 2025 23:10 1h 2m 43s main
main
August 28, 2025 23:10 1h 2m 43s
feat(draft_model): support draft_model for RemoteModelLoader (#6407) PR Test (Xeon) #11338: Commit a38c149 pushed by zhyncs
August 28, 2025 23:09 17s main
main
August 28, 2025 23:09 17s
[Feature] Support NPUGraph for DeepSeek on Ascend NPU (#9355) PR Test (Xeon) #11337: Commit 74dd424 pushed by zhyncs
August 28, 2025 23:06 3m 28s main
main
August 28, 2025 23:06 3m 28s
[HiCache] change the default policy to write through PR Test (Xeon) #11336: Pull request #9772 opened by xiezhq-hermann
August 28, 2025 23:02 36m 2s xiezhq-hicache-default
xiezhq-hicache-default
August 28, 2025 23:02 36m 2s
feat: add tuned fused moe config for GLM-4.5-Air-FP8 tp = 4 on B200 (… PR Test (Xeon) #11335: Commit dc20c22 pushed by zhyncs
August 28, 2025 23:00 38m 42s main
main
August 28, 2025 23:00 38m 42s
Support overlap scheduling for speculative decoding PR Test (Xeon) #11334: Pull request #9588 synchronize by thecodingwizard
August 28, 2025 22:32 34m 22s modal-labs:eagle-overlap
modal-labs:eagle-overlap
August 28, 2025 22:32 34m 22s