Skip to content

Pull requests: sgl-project/sglang

New pull request New
50 Open 2,018 Closed
50 Open 2,018 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

fix: Fix deprecated max_tokens param in openai ChatCompletionRequest
#3122 opened Jan 25, 2025 by mickqian Loading…
1 of 4 tasks
support fp32 in sampling_scaling_penalties kernel
#3121 opened Jan 25, 2025 by BBuf Loading…
5
Add EngineFragment
#3120 opened Jan 25, 2025 by fzyzcjy • Draft
4 tasks
[DO NOT MERGE] Bump CI to check
#3119 opened Jan 25, 2025 by fzyzcjy • Draft
4 tasks
Split communication logic from computation logic into orchestrator
#3118 opened Jan 25, 2025 by fzyzcjy • Draft
4 tasks
Let DetokenizerManager use TypeBasedDispatcher
#3117 opened Jan 25, 2025 by fzyzcjy • Draft
4 tasks
Rename TokenizerManager to StdOrchestrator
#3116 opened Jan 25, 2025 by fzyzcjy • Draft
4 tasks
Extract generation_manager from tokenizer_manager
#3115 opened Jan 25, 2025 by fzyzcjy • Draft
4 tasks
First draft on GSM8K benchmark.
#3114 opened Jan 24, 2025 by simveit • Draft
3 tasks
enable kv_scale for Gemma2
#3113 opened Jan 24, 2025 by hliuca Loading…
Set USE_VLLM_CUSTOM_ALLREDUCE to empty string
#3111 opened Jan 24, 2025 by tot0 Loading…
3 of 4 tasks
1
feat: use sgl-kernel by default
#3088 opened Jan 23, 2025 by zhyncs Loading…
4 tasks
2
Add CPU affinity setting to latency benchmark
#3085 opened Jan 23, 2025 by hubertlu-tw Loading…
4 tasks
2
[Feature] Beam Search
#3066 opened Jan 23, 2025 by laixinn Loading…
4 of 8 tasks
support w8a8 fp8 kernel with CUTLASS high priority
#3047 opened Jan 22, 2025 by HandH1998 Loading…
@ispobock @BBuf
@HandH1998 @zhyncs
23
Modify the kernel test path & add it to the CI process.
#3044 opened Jan 22, 2025 by sleepcoo Loading…
1
Support int8 kvcahe
#3034 opened Jan 21, 2025 by sleepcoo Loading…
@ispobock @HandH1998 @zhyncs
21
Debug radixcache: refactor recursive helper methods
#3029 opened Jan 21, 2025 by luzengxiangcn Loading…
3 of 4 tasks
2
Minicpmo
#3023 opened Jan 21, 2025 by mickqian • Draft
3 of 4 tasks
support telechat2 model
#3000 opened Jan 20, 2025 by shunxing12345 Loading…
4 tasks
5
Integrate turbomind into sgl-kernel
#2999 opened Jan 20, 2025 by bjmsong Loading…
4 tasks
@zhyncs
10
[Fix] Address remaining issues of supporting MiniCPMV
#2977 opened Jan 19, 2025 by mickqian Loading…
3 tasks done
17
[MOE] try to optimize cu kernel single block execution - distribute cumsum workload from thread 0 to other threads
#2970 opened Jan 19, 2025 by yiakwy-xpu-ml-framework-team Loading…
3 of 4 tasks
6
[Core] Optimize the delay scheduling of in batch prefix caching
#2962 opened Jan 18, 2025 by MrAta • Draft
4 tasks
Test removing a branch logic
#2905 opened Jan 15, 2025 by rkooo567 Loading…
3 tasks
1
ProTip! no:milestone will show everything without a milestone.