-
Notifications
You must be signed in to change notification settings - Fork 1.1k
Pull requests: sgl-project/sglang
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Fix block_shape in benchmark_vllm_vs_sglang_fused_moe_triton.py
#3858
opened Feb 25, 2025 by
zifeitong
Loading…
6 tasks done
Fix scripts/killall_sglang.sh and improve scripts/ci_install_dependency.sh
#3851
opened Feb 25, 2025 by
merrymercy
Loading…
Update FP8 kernel configuration for 4xGPU support on AMD
#3850
opened Feb 25, 2025 by
Eliovp
Loading…
[docs] Update outdated description about
torch.compile
#3844
opened Feb 25, 2025 by
junliu-mde
Loading…
2 of 6 tasks
[Doc] Fix typo in backend/sampling_params
#3835
opened Feb 25, 2025 by
yang-ybb
Loading…
2 of 6 tasks
[BugFix]: Add type check before compare for max_new_tokens
#3832
opened Feb 25, 2025 by
YangZeyu95
Loading…
1 of 6 tasks
[Eagle] small vocab table for draft model.
#3822
opened Feb 24, 2025 by
Zhou-sx
Loading…
1 of 6 tasks
Ensure Usage Data in Streaming Responses Aligns with vLLM’s Implementation
#3814
opened Feb 24, 2025 by
HermitSun
Loading…
1 of 6 tasks
Add model name in EntryClass for tracking doc update to date
#3800
opened Feb 24, 2025 by
zhengy001
Loading…
2 of 6 tasks
[QUANT] Add GPTQModel Dynamic Quantization +
lm_head
Quantization
#3790
opened Feb 22, 2025 by
Qubitium
Loading…
6 of 9 tasks
[ROCM MOE] Enable ROCM AITER Block MOE For DeepSeek R1/V3
#3788
opened Feb 22, 2025 by
BruceXcluding
Loading…
6 tasks done
[quant kernel] sgl-kernel support per_tensor_quant fp8
#3786
opened Feb 22, 2025 by
BBuf
Loading…
4 tasks done
Previous Next
ProTip!
Updated in the last three days: updated:>2025-02-22.