Skip to content

Actions: sgl-project/sglang

Cancel PR Workflows on Merge

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
761 workflow run results
761 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Minor] Fix styles for overlap mode
Cancel PR Workflows on Merge #686: Pull request #2068 closed by merrymercy
November 18, 2024 03:49 12s
November 18, 2024 03:49 12s
add phi-3 small support
Cancel PR Workflows on Merge #685: Pull request #2062 closed by merrymercy
November 18, 2024 02:47 11s
November 18, 2024 02:47 11s
[Performance] Update xgrammar-related constrained decoding
Cancel PR Workflows on Merge #684: Pull request #2056 closed by merrymercy
November 18, 2024 00:58 10s
November 18, 2024 00:58 10s
Rename arguments --disable-nan-detection to --enable-nan-detection
Cancel PR Workflows on Merge #683: Pull request #2066 closed by merrymercy
November 18, 2024 00:53 13s
November 18, 2024 00:53 13s
Support cuda graph for DP attention
Cancel PR Workflows on Merge #682: Pull request #2061 closed by merrymercy
November 18, 2024 00:29 15s
November 18, 2024 00:29 15s
Deprecate --disable-flashinfer and --disable-flashinfer-sampling
Cancel PR Workflows on Merge #681: Pull request #2065 closed by merrymercy
November 18, 2024 00:21 13s
November 18, 2024 00:21 13s
Remove monkey_patch_vllm_dummy_weight_loader
Cancel PR Workflows on Merge #680: Pull request #2064 closed by merrymercy
November 17, 2024 23:48 14s
November 17, 2024 23:48 14s
Revert "chore: update torch v2.5.1"
Cancel PR Workflows on Merge #679: Pull request #2063 closed by merrymercy
November 17, 2024 23:29 17s
November 17, 2024 23:29 17s
chore: update torch v2.5.1
Cancel PR Workflows on Merge #678: Pull request #1849 closed by zhyncs
November 17, 2024 16:06 12s
November 17, 2024 16:06 12s
Launch dp ranks in parallel
Cancel PR Workflows on Merge #677: Pull request #2053 closed by merrymercy
November 17, 2024 01:13 11s
November 17, 2024 01:13 11s
Fix illegal memory access in overlap mode & Use more fused triton kernels for building meta data
Cancel PR Workflows on Merge #676: Pull request #2051 closed by merrymercy
November 17, 2024 00:14 14s
November 17, 2024 00:14 14s
Support DP MLA
Cancel PR Workflows on Merge #675: Pull request #1970 closed by merrymercy
November 16, 2024 09:01 10s
November 16, 2024 09:01 10s
Fix weight update for data parallelism
Cancel PR Workflows on Merge #674: Pull request #2050 closed by merrymercy
November 16, 2024 08:30 14s
November 16, 2024 08:30 14s
Add get_amdgpu_memory_capacity()
Cancel PR Workflows on Merge #673: Pull request #2049 closed by ByronHsu
November 16, 2024 06:51 11s
November 16, 2024 06:51 11s
Add Tensor Parallel to torch_native_llama
Cancel PR Workflows on Merge #672: Pull request #1876 closed by merrymercy
November 16, 2024 05:26 14s
November 16, 2024 05:26 14s
Fix core (MI300X) with --enable-overlap
Cancel PR Workflows on Merge #671: Pull request #2048 closed by merrymercy
November 16, 2024 05:24 14s
November 16, 2024 05:24 14s
fix a small typo in docs
Cancel PR Workflows on Merge #670: Pull request #2047 closed by merrymercy
November 15, 2024 19:09 16s
November 15, 2024 19:09 16s
Release v0.3.5.post2
Cancel PR Workflows on Merge #669: Pull request #2046 closed by merrymercy
November 15, 2024 14:54 14s
November 15, 2024 14:54 14s
[Fix] Adjust default chunked prefill size and cuda graph max bs according to GPU memory capacity
Cancel PR Workflows on Merge #668: Pull request #2044 closed by merrymercy
November 15, 2024 14:21 15s
November 15, 2024 14:21 15s
Fix json benchmark
Cancel PR Workflows on Merge #667: Pull request #2043 closed by merrymercy
November 15, 2024 13:33 14s
November 15, 2024 13:33 14s
benchmark json schema
Cancel PR Workflows on Merge #666: Pull request #2030 closed by merrymercy
November 15, 2024 13:06 12s
November 15, 2024 13:06 12s
Fix the default arguments of bench_offline_throughput.py & simplify detokenizer manager
Cancel PR Workflows on Merge #665: Pull request #2042 closed by merrymercy
November 15, 2024 13:02 16s
November 15, 2024 13:02 16s
fix: align enable_overlap_scheduler naming between code and docs
Cancel PR Workflows on Merge #664: Pull request #2038 closed by merrymercy
November 15, 2024 11:39 13s
November 15, 2024 11:39 13s
Offline LLM Engine Benchmark Throughput
Cancel PR Workflows on Merge #663: Pull request #1968 closed by ByronHsu
November 15, 2024 05:59 15s
November 15, 2024 05:59 15s
Expose no_stop_trim and skip_special_tokens in openai api
Cancel PR Workflows on Merge #662: Pull request #2039 closed by merrymercy
November 15, 2024 03:09 13s
November 15, 2024 03:09 13s