SGLang issues | Ecosyste.ms: OpenCollective

[Router] remove duplicate char count

github.com/sgl-project/sglang - ByronHsu opened this pull request 28 days ago

Fix the overlap for xgrammar

github.com/sgl-project/sglang - merrymercy opened this pull request 28 days ago

[Feature] Support EBNF in xgrammar

github.com/sgl-project/sglang - merrymercy opened this issue 28 days ago

Release v0.4.0.post1

github.com/sgl-project/sglang - merrymercy opened this pull request 28 days ago

Use proc.join instead of busy waiting

github.com/sgl-project/sglang - merrymercy opened this pull request 28 days ago

docs: update adoption (Meituan)

github.com/sgl-project/sglang - zhyncs opened this pull request 28 days ago

[Feature] lora serving performance

github.com/sgl-project/sglang - MichoChan opened this issue 28 days ago

MoE Expert Parallel

github.com/sgl-project/sglang - xiaobochen123 opened this pull request 28 days ago

Move FP8 to SGLang

github.com/sgl-project/sglang - zhyncs opened this pull request 28 days ago

[router] support `/add_worker` api

github.com/sgl-project/sglang - ByronHsu opened this pull request 28 days ago

[router] use 2-gpu-runner

github.com/sgl-project/sglang - ByronHsu opened this pull request 29 days ago

[Bug] sglang isn't compatible with latest vLLM

github.com/sgl-project/sglang - hliuca opened this issue 29 days ago

Move FP8 to sglang

github.com/sgl-project/sglang - HaiShaw opened this pull request 29 days ago

Qwen2vl vision encoder fix

github.com/sgl-project/sglang - jakep-allenai opened this pull request 29 days ago

Fix AWQ with enable MLA

github.com/sgl-project/sglang - ispobock opened this pull request 29 days ago

docs: Improve instructions for supporting new models

github.com/sgl-project/sglang - vchzls opened this pull request 29 days ago

[Bug] deepseek v2.5 w4a16 can not run

github.com/sgl-project/sglang - cxmt-ai-tc opened this issue 29 days ago

[Bug] sglang-router failure

github.com/sgl-project/sglang - fengyang95 opened this issue 29 days ago

optimize cuda graph max_bs_settings on low-end gpus

github.com/sgl-project/sglang - BBuf opened this pull request 29 days ago

Fix the cuda graph capture range for small #max-running-requests

github.com/sgl-project/sglang - merrymercy opened this pull request 29 days ago

[Bug] runtime_endpoint encounter a JSONDecodeError

github.com/sgl-project/sglang - huyiwen opened this issue 29 days ago

Add more support for intel Gaudi accelerators

github.com/sgl-project/sglang - YangQun1 opened this pull request 29 days ago

[Bug] ValueError: Model architectures ['Qwen2ForCausalLM'] are not supported for now. Supported architectures: dict_keys(['CohereForCausalLM', 'DbrxForCausalLM', 'GPT2LMHeadModel', 'GPTBigCodeForCausalLM', 'OlmoForCausalLM', 'Phi3SmallForCausalLM', 'StableLmForCausalLM', 'XverseForCausalLM', 'XverseMoeForCausalLM'])

github.com/sgl-project/sglang - Trangle opened this issue 29 days ago

[Minor] Code style improvements

github.com/sgl-project/sglang - merrymercy opened this pull request 29 days ago

[Bug] tp == 2 model gibberish

github.com/sgl-project/sglang - chalo2000 opened this issue 30 days ago

Dynamo doesn't handle branching on AsyncCollectiveTensor well

github.com/sgl-project/sglang - bdhirsh opened this issue 30 days ago

Make torch TP composable with torch.compile

github.com/sgl-project/sglang - kwen2501 opened this pull request 30 days ago

[Feature] Support mistralai/Pixtral

github.com/sgl-project/sglang - merrymercy opened this issue 30 days ago

minor: limit the range of vllm versions

github.com/sgl-project/sglang - zhyncs opened this pull request 30 days ago

MLA prefill w/o weight absorption

github.com/sgl-project/sglang - ispobock opened this pull request 30 days ago

Adding SGLang FP8 Utils

github.com/sgl-project/sglang - HaiShaw opened this pull request about 1 month ago

[Bug] Re-enable fused_moe_triton on AMD

github.com/sgl-project/sglang - HaiShaw opened this issue about 1 month ago

[Bug] qwen2-vl is incompatible with torch compile

github.com/sgl-project/sglang - wellhowtosay opened this issue about 1 month ago

[Feature] Serving VLM VILA

github.com/sgl-project/sglang - anhnhust opened this issue about 1 month ago

[Bug] alignment error when continuous batching and disable radix_tree_cache

github.com/sgl-project/sglang - kaixarider opened this issue about 1 month ago

[Feature] router adds add_worker_url, remove_worker_url api

github.com/sgl-project/sglang - 81549361 opened this issue about 1 month ago

move apply_torchao_config_ to model_runner

github.com/sgl-project/sglang - jerryzh168 opened this pull request about 1 month ago

docs: add SGLang v0.4 blog

github.com/sgl-project/sglang - zhyncs opened this pull request about 1 month ago

Check gpu availability at server args creation

github.com/sgl-project/sglang - MrAta opened this pull request about 1 month ago

[router] Copy license when publishing & bump version

github.com/sgl-project/sglang - ByronHsu opened this pull request about 1 month ago

chore: bump v0.4.0

github.com/sgl-project/sglang - zhyncs opened this pull request about 1 month ago

[Feature] use SGLang's FusedMoE with quantization

github.com/sgl-project/sglang - zhyncs opened this issue about 1 month ago

[Feature] support AWQ with enable MLA

github.com/sgl-project/sglang - zhyncs opened this issue about 1 month ago

fix: resolve cmake url for Dockerfile.dev

github.com/sgl-project/sglang - zhyncs opened this pull request about 1 month ago

[kernel] introduce fused_moe_triton_splitk optimization

github.com/sgl-project/sglang - BBuf opened this pull request about 1 month ago

[kernel] introduce fused_moe_triton_splitk to sglang

github.com/sgl-project/sglang - BBuf opened this pull request about 1 month ago

[Feature] how to use tp or dp in offline engine?

github.com/sgl-project/sglang - chesterout opened this issue about 1 month ago

Fix shape error that occurred when loading lora weight of gemma2 model.

github.com/sgl-project/sglang - upskyy opened this pull request about 1 month ago

Revert "[feat] Enable chunked prefill for llava-onevision"

github.com/sgl-project/sglang - Ying1123 opened this pull request about 1 month ago

ROCm Container: set SGLANG_SET_CPU_AFFINITY=1

github.com/sgl-project/sglang - HaiShaw opened this pull request about 1 month ago

Improve torch compile for fused moe

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

[Minor] Fix logger and style

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

Add missing license for router wheel

github.com/sgl-project/sglang - MrAta opened this pull request about 1 month ago

Fix Docs CI When Compile Error

github.com/sgl-project/sglang - zhaochenyang20 opened this pull request about 1 month ago

[Bug] Update weights from disk ends in runtime corruption for different size model

github.com/sgl-project/sglang - zhaochenyang20 opened this issue about 1 month ago

Adapt vllm custom ar into sgl-kernel

github.com/sgl-project/sglang - yizhang2077 opened this pull request about 1 month ago

[Feature] Enable SGLang on more AMD GPUs

github.com/sgl-project/sglang - HaiShaw opened this issue about 1 month ago

Relax to include more AMD GPUs

github.com/sgl-project/sglang - HaiShaw opened this pull request about 1 month ago

Update model_loader deps and qqq quantization deps (#2220)

github.com/sgl-project/sglang - zhyncs opened this pull request about 1 month ago

[Feature] add Dockerfile dev image and doc

github.com/sgl-project/sglang - zhyncs opened this issue about 1 month ago

Master

github.com/sgl-project/sglang - ykcombat opened this pull request about 1 month ago

[Bug] fix code scanning issue

github.com/sgl-project/sglang - zhyncs opened this issue about 1 month ago

Add more fused moe benchmark utilities

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

[Feature] Specify dtype at begin_forward for FlashInfer > 0.1.6

github.com/sgl-project/sglang - zhyncs opened this issue about 1 month ago

[Bug] Overlap mode scheduler doesn't work for bench_serving with given request rate

github.com/sgl-project/sglang - ykcombat opened this issue about 1 month ago

[Minor] Fix code style

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

Use rocminfo instead of rocm-smi for more OS/WSL support

github.com/sgl-project/sglang - HaiShaw opened this pull request about 1 month ago

[Fix] Fix the padded hash value for image tokens

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

Add Docs For SGLang Native Router

github.com/sgl-project/sglang - zhaochenyang20 opened this pull request about 1 month ago

misc: Fix typo "resulve" to "resolve"

github.com/sgl-project/sglang - Edenzzzz opened this pull request about 1 month ago

misc: update build setup

github.com/sgl-project/sglang - zhyncs opened this pull request about 1 month ago

fix: resolve CodeQL cpp issue

github.com/sgl-project/sglang - zhyncs opened this pull request about 1 month ago

feat: use warp reduce as a simple example

github.com/sgl-project/sglang - zhyncs opened this pull request about 1 month ago

[Feature] make the compilation of torch.compile faster

github.com/sgl-project/sglang - merrymercy opened this issue about 1 month ago

feat: support sgl-kernel pypi

github.com/sgl-project/sglang - zhyncs opened this pull request about 1 month ago

Fix logprob for completions

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

Fix gptq for moe layers

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

minor: rm unused _grouped_size_compiled_for_decode_kernels

github.com/sgl-project/sglang - zhyncs opened this pull request about 1 month ago

feat: skip good first issue

github.com/sgl-project/sglang - zhyncs opened this pull request about 1 month ago

[Feature] sgl-kernel pipelines

github.com/sgl-project/sglang - zhyncs opened this issue about 1 month ago

minor: support flashinfer nightly

github.com/sgl-project/sglang - zhyncs opened this pull request about 1 month ago

[Bug] EOFError

github.com/sgl-project/sglang - HuanzhiMao opened this issue about 1 month ago

[CI] Balance CI tests

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

Feat: upgrade outlines & support compatibility with the old version

github.com/sgl-project/sglang - gobraves opened this pull request about 1 month ago

[Feature] Support a custom logit processor

github.com/sgl-project/sglang - merrymercy opened this issue about 1 month ago

Fix chunked prefill when ignore eos

github.com/sgl-project/sglang - hnyls2002 opened this pull request about 1 month ago

feat: add Dockerfile for development

github.com/sgl-project/sglang - zhyncs opened this pull request about 1 month ago

[CI] Fix missing files in run_suite.py

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

Revert "Revert "[FEAT] Support GGUF format""

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

Revert "[Fix] fix assertion error for chunked prefill when disabling cache"

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

Revert "[FEAT] Support GGUF format"

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

[CI] Fix ci tests

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

[Fix] fix assertion error for chunked prefill when disabling cache

github.com/sgl-project/sglang - wangraying opened this pull request about 1 month ago

[feat] Enable chunked prefill for llava-onevision

github.com/sgl-project/sglang - Ying1123 opened this pull request about 1 month ago

[CI] Kill zombie processes

github.com/sgl-project/sglang - merrymercy opened this pull request about 1 month ago

Online weight updates from torch.distributed

github.com/sgl-project/sglang - zhaochenyang20 opened this pull request about 1 month ago

[Performance] Torch.compile is slow on MoE layers when bs > 1

github.com/sgl-project/sglang - merrymercy opened this issue about 1 month ago

[CI] Add accuracy test for multimodal models

github.com/sgl-project/sglang - merrymercy opened this issue about 1 month ago

[Feature] Support outlines >= 0.1

github.com/sgl-project/sglang - merrymercy opened this issue about 1 month ago

[CI] Print nightly evaluation results to GITHUB_STEP_SUMMARY

github.com/sgl-project/sglang - merrymercy opened this issue about 1 month ago