Skip to content

Actions: xLLM-AI/xllm

Actions

xLLM Build x86_64 CUDA

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build_x86_64_cuda.yaml
2,500+ workflow runs
2,500+ workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
feat: add xlite as third npu backend (support qwen3-dense/qwen3-moe/glm-4.7/glm-5.1/glm-5.2) xLLM Build x86_64 CUDA #10694: Pull request #2282 submitted by yinjiawei01
12m 32s
12m 32s
feat: add xlite as third npu backend (support qwen3-dense/qwen3-moe/glm-4.7/glm-5.1/glm-5.2) xLLM Build x86_64 CUDA #10693: Pull request #2282 submitted by yt-zeng
3s
3s
feat: add xlite as third npu backend (support qwen3-dense/qwen3-moe/glm-4.7/glm-5.1/glm-5.2) xLLM Build x86_64 CUDA #10692: Pull request #2282 submitted by ustcfy
4s
4s
feat: add xlite as third npu backend (support qwen3-dense/qwen3-moe/glm-4.7/glm-5.1/glm-5.2) xLLM Build x86_64 CUDA #10691: Pull request #2282 submitted by liutongxuan
10m 43s
10m 43s
feat: support qwen3 dspark decoding on NPU with Python executor. xLLM Build x86_64 CUDA #10690: Pull request #2263 submitted by zhang-minchao
14m 10s
14m 10s
feat: support qwen3 dspark decoding on NPU with Python executor. xLLM Build x86_64 CUDA #10689: Pull request #2263 submitted by ustcfy
44m 35s
44m 35s
feat: support Qwen3.5 Decode Context Parallel on Ascend NPU. xLLM Build x86_64 CUDA #10688: Pull request #2125 synchronize by Enguikong
1h 6m 3s Enguikong:feat/qwen35-dcp-correctness
Enguikong:feat/qwen35-dcp-correctness
1h 6m 3s
feat: support qwen3 dspark decoding on NPU with Python executor. xLLM Build x86_64 CUDA #10687: Pull request #2263 submitted by weizhehuang0827
56m 54s
56m 54s
feat: add lag confidence to decouple adaptive speculative pruning from critical path. xLLM Build x86_64 CUDA #10686: Pull request #2280 synchronize by weizhehuang0827
41m 4s weizhehuang0827:feat/adaptive-lag-confidence
weizhehuang0827:feat/adaptive-lag-confidence
41m 4s
feat: support Qwen3.5 Decode Context Parallel on Ascend NPU. xLLM Build x86_64 CUDA #10685: Pull request #2125 synchronize by Enguikong
10m 31s Enguikong:feat/qwen35-dcp-correctness
Enguikong:feat/qwen35-dcp-correctness
10m 31s
feat: support qwen3 dspark decoding on NPU with Python executor. xLLM Build x86_64 CUDA #10684: Pull request #2263 synchronize by yinjiawei01
24m 37s yinjiawei01:features/qwen3_dspark_python_npu
yinjiawei01:features/qwen3_dspark_python_npu
24m 37s
feat: support Qwen3.5 Decode Context Parallel on Ascend NPU. xLLM Build x86_64 CUDA #10683: Pull request #2125 synchronize by Enguikong
11m 32s Enguikong:feat/qwen35-dcp-correctness
Enguikong:feat/qwen35-dcp-correctness
11m 32s
feat: support Qwen3.5 Decode Context Parallel on Ascend NPU. xLLM Build x86_64 CUDA #10682: Pull request #2125 synchronize by Enguikong
11m 4s Enguikong:feat/qwen35-dcp-correctness
Enguikong:feat/qwen35-dcp-correctness
11m 4s
bugfix: separate greedy and probabilistic draft proposals for rejecti… xLLM Build x86_64 CUDA #10681: Commit 9e0f140 pushed by zhang-minchao
41m 46s main
main
41m 46s
feat: append vit executor for qwen3 vl model xLLM Build x86_64 CUDA #10680: Pull request #2207 synchronize by AmpereKowk
Action required AmpereKowk:qwen3_vl_executor
AmpereKowk:qwen3_vl_executor
Action required
feat: append vit executor for qwen3 vl model xLLM Build x86_64 CUDA #10679: Pull request #2207 synchronize by AmpereKowk
Action required AmpereKowk:qwen3_vl_executor
AmpereKowk:qwen3_vl_executor
Action required
feat: support EPLB for DeepSeek-V3.2 Python model executor. xLLM Build x86_64 CUDA #10678: Pull request #2283 opened by yingxudeng
37m 34s yingxudeng:feat/deepseek-v32-python-eplb
yingxudeng:feat/deepseek-v32-python-eplb
37m 34s
bugfix: separate greedy and probabilistic draft proposals for rejection sampling. xLLM Build x86_64 CUDA #10677: Pull request #2175 submitted by zhang-minchao
10m 57s
10m 57s
bugfix: separate greedy and probabilistic draft proposals for rejection sampling. xLLM Build x86_64 CUDA #10676: Pull request #2175 submitted by DongheJin
40m 41s
40m 41s
feat: add opt-in FIA decode for Qwen3.5. xLLM Build x86_64 CUDA #10675: Pull request #2240 submitted by Enguikong
1m 41s
1m 41s
feat: add opt-in FIA decode for Qwen3.5. xLLM Build x86_64 CUDA #10674: Pull request #2240 synchronize by Enguikong
7m 53s Enguikong:feat/qwen35-fia-decode
Enguikong:feat/qwen35-fia-decode
7m 53s
bugfix: make DSV4 SWA capacity PD-aware. xLLM Build x86_64 CUDA #10673: Pull request #2265 synchronize by Kang-Meng
42m 58s Kang-Meng:bugfix_swa
Kang-Meng:bugfix_swa
42m 58s
bugfix: make DSV4 SWA capacity PD-aware. xLLM Build x86_64 CUDA #10672: Pull request #2265 synchronize by Kang-Meng
5m 50s Kang-Meng:bugfix_swa
Kang-Meng:bugfix_swa
5m 50s
bugfix: make DSV4 SWA capacity PD-aware. xLLM Build x86_64 CUDA #10671: Pull request #2265 synchronize by Kang-Meng
24m 46s Kang-Meng:bugfix_swa
Kang-Meng:bugfix_swa
24m 46s
feat: add xlite as third npu backend (support qwen3-dense/qwen3-moe/glm-4.7/glm-5.1/glm-5.2) xLLM Build x86_64 CUDA #10670: Pull request #2282 synchronize by banxiaduhuo
5s banxiaduhuo:main
banxiaduhuo:main
5s