Skip to content

Actions: vllm-project/tpu-inference

Actions

Enforce Ready Label

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
check_ready_label.yml
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
Sync vLLM LKG to Last 0902 Commit Enforce Ready Label #13002: Pull request #3522 synchronize by patrickji2014
2h 4m 50s oncall.0827.sync_vllm_to_0902
oncall.0827.sync_vllm_to_0902
2h 4m 50s
Update tokamax pin to nightly on 20260903. Enforce Ready Label #13001: Pull request #3524 labeled by vanbasten23
2h 9m 0s xiowei/update_tokamax_pin_20260903
xiowei/update_tokamax_pin_20260903
2h 9m 0s
Update tokamax pin to nightly on 20260903. Enforce Ready Label #13000: Pull request #3524 opened by vanbasten23
2h 8m 23s xiowei/update_tokamax_pin_20260903
xiowei/update_tokamax_pin_20260903
2h 8m 23s
[kernels/flash_attention] Cap Scoped VMEM to 32MB and route Vision Tower SDPA to Flash Attention for large sequences Enforce Ready Label #12999: Pull request #3442 synchronize by amitkumar307d
10m 4s amitkumar307d:qwen-video-flash-attn
amitkumar307d:qwen-video-flash-attn
10m 4s
[models/vllm] Support multimodal dynamic sequence padding, TP device placement, and GridTHW PyTree registration Enforce Ready Label #12998: Pull request #3444 synchronize by amitkumar307d
45m 15s amitkumar307d:qwen-video-tp-padding
amitkumar307d:qwen-video-tp-padding
45m 15s
Sync vLLM LKG to Last 0902 Commit Enforce Ready Label #12997: Pull request #3522 labeled by patrickji2014
10m 53s oncall.0827.sync_vllm_to_0902
oncall.0827.sync_vllm_to_0902
10m 53s
[models/vllm] Add targeted AOT Vision Tower JIT precompilation warmup for video architectures Enforce Ready Label #12996: Pull request #3443 synchronize by amitkumar307d
7m 12s amitkumar307d:qwen-video-jit-warmup
amitkumar307d:qwen-video-jit-warmup
7m 12s
build(docker): build and package vllm-rs Rust frontend for TPU Enforce Ready Label #12995: Pull request #3523 opened by aojea
Action required aojea:feat/build-rust-frontend-tpu
aojea:feat/build-rust-frontend-tpu
Action required
Sync vLLM LKG to Last 0902 Commit Enforce Ready Label #12994: Pull request #3522 opened by patrickji2014
9m 7s oncall.0827.sync_vllm_to_0902
oncall.0827.sync_vllm_to_0902
9m 7s
[models/vllm] Support multimodal dynamic sequence padding, TP device placement, and GridTHW PyTree registration Enforce Ready Label #12993: Pull request #3444 synchronize by amitkumar307d
12m 10s amitkumar307d:qwen-video-tp-padding
amitkumar307d:qwen-video-tp-padding
12m 10s
[kernels/flash_attention] Cap Scoped VMEM to 32MB and route Vision Tower SDPA to Flash Attention for large sequences Enforce Ready Label #12992: Pull request #3442 synchronize by amitkumar307d
29m 17s amitkumar307d:qwen-video-flash-attn
amitkumar307d:qwen-video-flash-attn
29m 17s
Decoupled Dual Block Pools for Hybrid Mamba/GDN Prefix Caching in Align Mode Enforce Ready Label #12991: Pull request #3517 synchronize by pv97
6m 3s pv97:hybrid-kv-cache
pv97:hybrid-kv-cache
6m 3s
[CI] Skip DB reporting on benchmark failure and fix indentation Enforce Ready Label #12990: Pull request #3521 labeled by meiyeh123
8s dennis/bm-db-writing
dennis/bm-db-writing
8s
[CI] Skip DB reporting on benchmark failure and fix indentation Enforce Ready Label #12989: Pull request #3521 opened by meiyeh123
7s dennis/bm-db-writing
dennis/bm-db-writing
7s
[Bugfix] Report HBM across all local chips in the get_memory_info shim Enforce Ready Label #12988: Pull request #3505 synchronize by lxhfirenking
6s victorlxh/patch-get_memory_info
victorlxh/patch-get_memory_info
6s
[Bugfix] Report HBM across all local chips in the get_memory_info shim Enforce Ready Label #12987: Pull request #3505 synchronize by lxhfirenking
5s victorlxh/patch-get_memory_info
victorlxh/patch-get_memory_info
5s
Fix the Raiden RL weight-sync path Enforce Ready Label #12986: Pull request #3516 synchronize by A9isha
6s anisha/raiden-rl-weight-sync
anisha/raiden-rl-weight-sync
6s
Fix the Raiden RL weight-sync path Enforce Ready Label #12985: Pull request #3516 synchronize by A9isha
5s anisha/raiden-rl-weight-sync
anisha/raiden-rl-weight-sync
5s
Fix the Raiden RL weight-sync path Enforce Ready Label #12984: Pull request #3516 labeled by wenxindongwork
8s anisha/raiden-rl-weight-sync
anisha/raiden-rl-weight-sync
8s
[Perf/Fix] Flax loader: keep kv-cache output sharding instead of forcing one attention spec Enforce Ready Label #12983: Pull request #3519 opened by wenxindongwork
5s wxd-flax-kv-cache-keep-sharding
wxd-flax-kv-cache-keep-sharding
5s
[Perf/Fix] Configure heterogeneous KV cache sharding for GDN/Mamba in model_loader Enforce Ready Label #12982: Pull request #3515 synchronize by sierraisland
6s sierraq/fix-gdn-kv-cache-sharding
sierraq/fix-gdn-kv-cache-sharding
6s
Score the answer, not the reasoning, in MMLU/GPQA extraction Enforce Ready Label #12981: Pull request #3518 labeled by lxhfirenking
7s victorlxh/multichoice-benchmark-parsing
victorlxh/multichoice-benchmark-parsing
7s
Fix the Raiden RL weight-sync path Enforce Ready Label #12980: Pull request #3516 synchronize by A9isha
6s anisha/raiden-rl-weight-sync
anisha/raiden-rl-weight-sync
6s
Score the answer, not the reasoning, in MMLU/GPQA extraction Enforce Ready Label #12979: Pull request #3518 opened by lxhfirenking
1m 22s victorlxh/multichoice-benchmark-parsing
victorlxh/multichoice-benchmark-parsing
1m 22s
[Core][DP] Fix "Should not schedule a request that does nothing!" in DPScheduler Enforce Ready Label #12978: Pull request #3492 synchronize by csgoogle
Action required csgoogle:fix/dp-scheduler-stale-output-deadlock
csgoogle:fix/dp-scheduler-stale-output-deadlock
Action required