Skip to content

Actions: ModelTC/LightLLM

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
2,500+ workflow runs
2,500+ workflow runs

Filter by Workflow

⌥ + click/return to exclude

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 FlashQLA GDN prefill backend Pre-commit checks #4505: Pull request #1408 opened by sufubao
34s sufubao:support_flashqla
sufubao:support_flashqla
34s
fix: quarantine PD pages until transfer quiesces Pre-commit checks #4504: Pull request #1406 synchronize by sufubao
39s sufubao:fix/pd-nixl-page-release-order
sufubao:fix/pd-nixl-page-release-order
39s
fix: harden Anthropic PDF and image content handling Pre-commit checks #4503: Pull request #1407 opened by sufubao
36s sufubao:claude_code_support
sufubao:claude_code_support
36s
fix: quarantine PD pages until transfer quiesces Pre-commit checks #4502: Pull request #1406 synchronize by sufubao
33s sufubao:fix/pd-nixl-page-release-order
sufubao:fix/pd-nixl-page-release-order
33s
fix: quarantine PD pages until transfer quiesces Pre-commit checks #4501: Pull request #1406 synchronize by sufubao
29s sufubao:fix/pd-nixl-page-release-order
sufubao:fix/pd-nixl-page-release-order
29s
fix: quarantine PD pages until transfer quiesces Pre-commit checks #4500: Pull request #1406 opened by sufubao
32s sufubao:fix/pd-nixl-page-release-order
sufubao:fix/pd-nixl-page-release-order
32s
Cache aware for pd Pre-commit checks #4499: Pull request #1379 synchronize by hiworldwzj
46s cache_aware
cache_aware
46s
feat: fuse post-attention all-reduce and RMSNorm Pre-commit checks #4498: Pull request #1405 opened by sufubao
36s sufubao:fused-allreduce-rmsnorm
sufubao:fused-allreduce-rmsnorm
36s
fix stream fc for qwen3_coder Pre-commit checks #4497: Pull request #1364 synchronize by shihaobai
41s stream_fc
stream_fc
41s
feat: interleave CPU KV cache pages across NUMA nodes Pre-commit checks #4496: Pull request #1399 synchronize by sufubao
35s sufubao:cpu_cache_numa
sufubao:cpu_cache_numa
35s
feat: gc.freeze hot processes and disable gc during cudagraph capture Pre-commit checks #4495: Pull request #1382 synchronize by sufubao
38s sufubao:T2-gc-freeze
sufubao:T2-gc-freeze
38s
Cache aware for pd Pre-commit checks #4494: Pull request #1379 synchronize by hiworldwzj
38s cache_aware
cache_aware
38s
Cache aware for pd Pre-commit checks #4493: Pull request #1379 synchronize by hiworldwzj
41s cache_aware
cache_aware
41s
Cache aware for pd Pre-commit checks #4492: Pull request #1379 synchronize by hiworldwzj
40s cache_aware
cache_aware
40s
zero deepstack layers on slot when audio reuse (#1400) Docker #852: Commit 359a5b8 pushed by hiworldwzj
7m 49s main
main
7m 49s
zero deepstack layers on slot when audio reuse Pre-commit checks #4491: Pull request #1400 synchronize by hiworldwzj
39s fix_embed_cached
fix_embed_cached
39s
feat(quant): add triton fp8 w8a8 per-tensor quantization method Pre-commit checks #4490: Pull request #1404 synchronize by sufubao
33s sufubao:support_fp8_pt
sufubao:support_fp8_pt
33s
feat(quant): add triton fp8 w8a8 per-tensor quantization method Pre-commit checks #4489: Pull request #1404 synchronize by shihaobai
1m 18s sufubao:support_fp8_pt
sufubao:support_fp8_pt
1m 18s
feat(quant): add triton fp8 w8a8 per-tensor quantization method Pre-commit checks #4488: Pull request #1404 synchronize by shihaobai
35s sufubao:support_fp8_pt
sufubao:support_fp8_pt
35s
feat(quant): add triton fp8 w8a8 per-tensor quantization method Pre-commit checks #4487: Pull request #1404 synchronize by sufubao
43s sufubao:support_fp8_pt
sufubao:support_fp8_pt
43s
feat(quant): add triton fp8 w8a8 per-tensor quantization method Pre-commit checks #4486: Pull request #1404 synchronize by shihaobai
36s sufubao:support_fp8_pt
sufubao:support_fp8_pt
36s
feat(quant): add triton fp8 w8a8 per-tensor quantization method Pre-commit checks #4485: Pull request #1404 opened by sufubao
32s sufubao:support_fp8_pt
sufubao:support_fp8_pt
32s
feat: support /v1/responses (#1384) Docker #851: Commit 451c1bf pushed by hiworldwzj
36m 52s main
main
36m 52s
fix: correct fialed->failed typo in Exception message (#1376) Docker #850: Commit b8d150b pushed by shihaobai
43m 35s main
main
43m 35s
fix: improve Qwen3.5 MTP accept rate (#1402) Docker #849: Commit 20ad042 pushed by shihaobai
57m 50s main
main
57m 50s