Skip to content

Pull requests: sgl-project/sglang

New pull request New
136 Open 2,648 Closed
136 Open 2,648 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

Support page size > 1
#4356 opened Mar 12, 2025 by merrymercy Loading…
2 tasks
2
Implement triton per token quantization of fp8
#4349 opened Mar 12, 2025 by zcnrex Loading…
6 tasks
Add Logits tests for Qwen2.5VL
#4347 opened Mar 12, 2025 by ravi03071991 • Draft
6 tasks
[AMD] Add Optimization for DeepSeek-R1/V3 based on AITER Backend
#4344 opened Mar 12, 2025 by BruceXcluding • Draft
7 tasks
@HaiShaw
1
Integrate DeepGemm contiguous group gemm into Fused MoE high priority
#4343 opened Mar 12, 2025 by laixinn • Draft
6 tasks done
[k8s] Clarified the usage of shared memory.
#4341 opened Mar 12, 2025 by jsuchome Loading…
2 of 6 tasks
8
Fix Llama3.3 tool call support high priority
#4320 opened Mar 11, 2025 by CatherineSue Loading…
3 of 6 tasks
@zhyncs
4
[quant kernel] sgl-kernel support per_token_quant int8
#4318 opened Mar 11, 2025 by zcnrex • Draft
6 tasks
3
[Feature] Support "strict" in function calling
#4310 opened Mar 11, 2025 by DarkSharpness Loading…
3 of 6 tasks
1
Add make_layers for deepseek_v2
#4307 opened Mar 11, 2025 by CharlesRiggins Loading…
6 tasks
1
add moe topk softmax templated from vllm to improve
#4302 opened Mar 11, 2025 by qingquansong • Draft
6 tasks
[Fix] Fix a bug when calculating m in benchmark_lightning_attention_prefill.py
#4294 opened Mar 11, 2025 by xiefan46 Loading…
6 tasks
1
Add --metrics-flush-interval flag to solve metrics sticking
#4285 opened Mar 11, 2025 by kebe7jun Loading…
1
3
Add metrics for tokenization/detokenization/wait in queue latency
#4280 opened Mar 11, 2025 by hebiao064 Loading…
1 of 6 tasks
[Feature] Support Tensor Parallelism and Weight Slicing for Lora
#4274 opened Mar 10, 2025 by aoshen524 Loading…
3 of 4 tasks
@Ying1123 @Fridge003
19
Fix the output of hidden states after HTTP requests
#4269 opened Mar 10, 2025 by Qiaolin-Yu Loading…
1 of 6 tasks
@merrymercy
6
Apply structured output sampling after reasoning steps in Reasoning models
#4264 opened Mar 10, 2025 by minleminzui Loading…
6 tasks done
5
remove moe_align vllm dep
#4249 opened Mar 10, 2025 by sleepcoo Loading…
1
[Feature] Support EAGLE 3 high priority
#4247 opened Mar 10, 2025 by chromecast56 Loading…
6 tasks
@Ying1123 @merrymercy @ispobock
26
Integrate DeepEP into SGLang high priority
#4232 opened Mar 9, 2025 by liz-badada • Draft
1 of 6 tasks
@merrymercy
11
[Feature] Prefill assistant response - add continue_final_message parameter
#4226 opened Mar 9, 2025 by adarshxs Loading…
3 tasks done
5
Statistical Analysis of the Output Stability of the Deepseek Model
#4202 opened Mar 8, 2025 by tanzelin430 • Draft
2 of 6 tasks
22
Fix MoE quant args
#4190 opened Mar 8, 2025 by Edenzzzz Loading…
6 tasks
1
[ROCm/Draft/No-Merge]: Flex Attention Enablement amd collaboration documentation Improvements or additions to documentation
#4172 opened Mar 7, 2025 by HaiShaw • Draft
6 tasks
[ROCm] Enable silu_and_mul, gelu_and_mul, gelu_tanh_and_mul in amd platform
#4150 opened Mar 6, 2025 by yiakwy-xpu-ml-framework-team Loading…
6 tasks
1
ProTip! Updated in the last three days: updated:>2025-03-09.