Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / sgl-project/sglang issues and pull requests
#1470 - Release v0.3.1.post2
Pull Request -
State: closed - Opened by merrymercy about 14 hours ago
#1469 - Fix padding in the cuda graph
Pull Request -
State: closed - Opened by merrymercy about 15 hours ago
#1467 - [Bug] illegal memory access encountered
Issue -
State: open - Opened by wonderisland about 15 hours ago
#1466 - [Bug] enable-mixed-chunk may cause the regex request get wrong result and output_token_logprobs
Issue -
State: open - Opened by liuteng about 15 hours ago
#1465 - Debug
Pull Request -
State: open - Opened by hnyls2002 about 15 hours ago
#1464 - fix: creat new dict everytime for putting new frame
Pull Request -
State: closed - Opened by Luodian about 17 hours ago
#1463 - [Bug] oom,torch.OutOfMemoryError: seems to only use one gpu on A800-80G,available 40g on each card
Issue -
State: open - Opened by chuangzhidan about 18 hours ago
- 3 comments
#1461 - Metrics
Pull Request -
State: open - Opened by binarycrayon about 20 hours ago
- 1 comment
#1460 - [Question]Why is the default value of max_prefill_tokens 16384?
Issue -
State: closed - Opened by wjj19950828 about 20 hours ago
#1459 - [WIP] Support double sparsity
Pull Request -
State: open - Opened by andy-yang-1 1 day ago
- 1 comment
#1458 - [Event] Add public meeting invite to README
Pull Request -
State: closed - Opened by Ying1123 1 day ago
#1457 - Fuse top_k and top_k in the sampler
Pull Request -
State: closed - Opened by merrymercy 1 day ago
#1456 - Pr fix max workers
Pull Request -
State: open - Opened by wellhowtosay 1 day ago
#1455 - [Bug] OOM when runing `bench_serving` with DeepSeekCoder-V2-Lite.
Issue -
State: closed - Opened by zh-zheng 1 day ago
- 2 comments
#1454 - Fix oom issues with fp8 for llama
Pull Request -
State: closed - Opened by merrymercy 1 day ago
#1453 - [Bugfix] Enable SGLang on AMD GPUs via PyTorch for ROCm (#1419)
Pull Request -
State: closed - Opened by HaiShaw 1 day ago
#1452 - Add bench_server_latency.py
Pull Request -
State: closed - Opened by merrymercy 1 day ago
#1451 - Fix schedule bug
Pull Request -
State: closed - Opened by hnyls2002 1 day ago
#1450 - fix schedule bug
Pull Request -
State: closed - Opened by hnyls2002 2 days ago
#1449 - Fixed n>1 causing list index out of range with VLM
Pull Request -
State: closed - Opened by jasonyux 2 days ago
- 2 comments
#1448 - Fix attention backend
Pull Request -
State: closed - Opened by ispobock 2 days ago
#1447 - Enable MLA by default
Pull Request -
State: closed - Opened by ispobock 2 days ago
#1446 - [Bug] Performance issue on MoE with torch.compile
Issue -
State: open - Opened by ispobock 3 days ago
Labels: performance
#1445 - Release 0.3.1.post1
Pull Request -
State: closed - Opened by merrymercy 3 days ago
#1444 - Add OLMoE model
Pull Request -
State: closed - Opened by janimo 3 days ago
#1443 - [Bug] The latest Sglang docker image cannot start online services
Issue -
State: closed - Opened by CedricHwong 3 days ago
- 2 comments
#1442 - Fix torch compile for deepseek-v2
Pull Request -
State: closed - Opened by ispobock 3 days ago
- 6 comments
#1441 - Simplify sampler and its error handling
Pull Request -
State: closed - Opened by merrymercy 3 days ago
#1440 - Clean up model loader
Pull Request -
State: closed - Opened by merrymercy 3 days ago
#1439 - [Bug] Llama 405B FP8 causes OOM on 16xA40
Issue -
State: open - Opened by sumukshashidhar 3 days ago
#1438 - Add constrained_json_whitespace_pattern to ServerArgs
Pull Request -
State: closed - Opened by zifeitong 3 days ago
#1436 - [Feature] Add initial support for sequence parallelism
Pull Request -
State: open - Opened by Ying1123 4 days ago
#1435 - [Feature] Expert parallelism support
Issue -
State: open - Opened by chongli-uw 4 days ago
Labels: enhancement
#1434 - [Bug] Nonsense and slow output under high concurrency
Issue -
State: open - Opened by tongyx361 4 days ago
- 1 comment
#1433 - [Feature] Support LoRA path renaming and add LoRA serving benchmarks
Pull Request -
State: closed - Opened by Ying1123 4 days ago
#1432 - Revert "[Minor] Raise exception for wrong import (#1409)"
Pull Request -
State: closed - Opened by Ying1123 4 days ago
#1431 - Remove deprecated configs
Pull Request -
State: closed - Opened by merrymercy 4 days ago
#1430 - Release v0.3.1
Pull Request -
State: closed - Opened by merrymercy 4 days ago
#1429 - Update backend.md
Pull Request -
State: closed - Opened by merrymercy 5 days ago
#1428 - [Fix] Fix logprob and normalized_logprob
Pull Request -
State: closed - Opened by merrymercy 5 days ago
#1427 - Add libibverbs-dev to Dockerfile
Pull Request -
State: closed - Opened by Aphoh 5 days ago
#1426 - fix: resolve nightly eval
Pull Request -
State: closed - Opened by zhyncs 5 days ago
#1425 - Add pytorch sampling backend ut
Pull Request -
State: closed - Opened by ispobock 5 days ago
#1424 - [Bug] missing max_workers param when initiate ProcessPoolExecutor
Issue -
State: open - Opened by wellhowtosay 6 days ago
- 2 comments
#1423 - [Bug] MLA models can't use enable-torch-compile. Can be fix by suppressing errors.
Issue -
State: closed - Opened by Achazwl 6 days ago
- 1 comment
#1422 - Enable torch.compile for triton backend
Pull Request -
State: closed - Opened by merrymercy 6 days ago
- 1 comment
#1421 - [Bug] deepseek-v2 fp8 cuda graph errror
Issue -
State: closed - Opened by fengyang95 6 days ago
- 5 comments
#1420 - [Feature, Hardware] Enable SGLang on AMD GPUs via PyTorch for ROCm
Pull Request -
State: closed - Opened by HaiShaw 6 days ago
#1419 - [Feature] Support AMD GPU via PyTorch for ROCm
Issue -
State: open - Opened by HaiShaw 6 days ago
Labels: enhancement
#1418 - Add torchao quant for mixtral and qwen_moe
Pull Request -
State: closed - Opened by jerryzh168 6 days ago
Labels: quant
#1417 - fallback to round robin scheduler
Pull Request -
State: open - Opened by qeternity 6 days ago
- 5 comments
#1416 - [Bug] AttributeError: 'MiniCPM3ForCausalLM' object has no attribute 'get_module_name'
Issue -
State: open - Opened by lixiangtiandashen 6 days ago
- 2 comments
#1415 - [Bug] Issue with batch API
Issue -
State: open - Opened by dmakhervaks 6 days ago
- 3 comments
#1414 - ci: fix finish
Pull Request -
State: closed - Opened by zhyncs 6 days ago
- 1 comment
#1413 - [Bug] triton attention-backend bug
Issue -
State: open - Opened by 81549361 6 days ago
#1412 - Update pr-test.yml
Pull Request -
State: closed - Opened by merrymercy 7 days ago
#1411 - Balance test in CI
Pull Request -
State: closed - Opened by merrymercy 7 days ago
#1410 - Update pr-test.yml
Pull Request -
State: closed - Opened by merrymercy 7 days ago
#1409 - [Minor] Raise exception for wrong import
Pull Request -
State: closed - Opened by Ying1123 7 days ago
- 2 comments
#1408 - [CI] Include triton backend and online serving benchmark into CI
Pull Request -
State: closed - Opened by merrymercy 7 days ago
#1407 - Make stop reason a dict instead of str
Pull Request -
State: closed - Opened by merrymercy 7 days ago
- 1 comment
#1406 - [Minor, CI] remove lora test from minimal suite
Pull Request -
State: closed - Opened by Ying1123 7 days ago
#1405 - [Bug] RuntimeError: Failed to allocate memory for batch_prefill_tmp_v with size 458752000 and alignment 16 in AlignedAllocator
Issue -
State: open - Opened by josephydu 7 days ago
- 3 comments
#1405 - [Bug] RuntimeError: Failed to allocate memory for batch_prefill_tmp_v with size 458752000 and alignment 16 in AlignedAllocator
Issue -
State: open - Opened by josephydu 7 days ago
- 3 comments
#1404 - [Bug] ImportError : cannot import name 'gemma_fused_add_rmsnorm' from 'flashinfer.norm'
Issue -
State: closed - Opened by luo647 8 days ago
- 2 comments
#1404 - [Bug] ImportError : cannot import name 'gemma_fused_add_rmsnorm' from 'flashinfer.norm'
Issue -
State: closed - Opened by luo647 8 days ago
- 1 comment
#1403 - kernel: use tensor cores for flashinfer gqa kernels
Pull Request -
State: closed - Opened by yzh119 8 days ago
- 1 comment
#1403 - kernel: use tensor cores for flashinfer gqa kernels
Pull Request -
State: closed - Opened by yzh119 8 days ago
- 1 comment
#1402 - [Minor Fix] Fix llava modalities issue for single-image
Pull Request -
State: closed - Opened by kcz358 8 days ago
- 1 comment
#1402 - [Minor Fix] Fix llava modalities issue for single-image
Pull Request -
State: closed - Opened by kcz358 8 days ago
- 1 comment
#1401 - Support cuda graph in the triton attention backend
Pull Request -
State: closed - Opened by merrymercy 8 days ago
- 4 comments
#1401 - Support cuda graph in the triton attention backend
Pull Request -
State: closed - Opened by merrymercy 8 days ago
- 5 comments
#1400 - [Bug] LLaVA performance inconsistent with the result
Issue -
State: closed - Opened by kcz358 8 days ago
- 1 comment
#1400 - [Bug] LLaVA performance inconsistent with the result
Issue -
State: closed - Opened by kcz358 8 days ago
- 1 comment
#1399 - Fix README format
Pull Request -
State: closed - Opened by Achazwl 8 days ago
#1397 - Add Support for XVERSE Models (Dense and MoE) to sglang
Pull Request -
State: closed - Opened by hxer7963 8 days ago
#1396 - [Feature] support awq of deepseek-v2 or deepseek-v2.5
Issue -
State: open - Opened by tutu329 8 days ago
#1396 - [Feature] support awq of deepseek-v2 or deepseek-v2.5
Issue -
State: open - Opened by tutu329 8 days ago
#1395 - [Feature] need DeepSeek-v2 or deepseek-v2.5 awq support
Issue -
State: closed - Opened by tutu329 8 days ago
#1395 - [Feature] need DeepSeek-v2 or deepseek-v2.5 awq support
Issue -
State: closed - Opened by tutu329 8 days ago
#1394 - Remove synchronization in cuda graph replay
Pull Request -
State: closed - Opened by hnyls2002 8 days ago
#1393 - Add no commit to main rule
Pull Request -
State: closed - Opened by hnyls2002 8 days ago
- 1 comment
#1392 - Optimize conflicts between CUDA graph and vocab mask tensors
Pull Request -
State: closed - Opened by hnyls2002 8 days ago
#1391 - [Bug] 'LlamaTokenizerFast' object has no attribute 'tokenizer'
Issue -
State: open - Opened by zwc163 8 days ago
#1391 - [Bug] 'LlamaTokenizerFast' object has no attribute 'tokenizer'
Issue -
State: closed - Opened by zwc163 8 days ago
#1390 - Improve error reporting during server launch
Pull Request -
State: closed - Opened by merrymercy 8 days ago
#1389 - [Fix] Fix --disable-flashinfer
Pull Request -
State: closed - Opened by merrymercy 8 days ago
- 1 comment
#1389 - [Fix] Fix --disable-flashinfer
Pull Request -
State: closed - Opened by merrymercy 8 days ago
- 1 comment
#1388 - [Feature] Support torch profiler
Issue -
State: open - Opened by danielhua23 9 days ago
- 1 comment
Labels: good first issue
#1388 - [Feature] Support torch profiler
Issue -
State: open - Opened by danielhua23 9 days ago
- 1 comment
Labels: good first issue
#1387 - [Feature] Can centos7 use this project?
Issue -
State: open - Opened by luo647 9 days ago
- 1 comment
#1387 - [Feature] Can centos7 use this project?
Issue -
State: closed - Opened by luo647 9 days ago
- 3 comments
#1386 - [Bug] requests.exceptions.JSONDecodeError:
Issue -
State: closed - Opened by eyuansu62 9 days ago
- 6 comments
#1386 - [Bug] requests.exceptions.JSONDecodeError:
Issue -
State: closed - Opened by eyuansu62 9 days ago
- 6 comments
#1385 - remove assertion in triton attention and add an unit test
Pull Request -
State: closed - Opened by ByronHsu 9 days ago
#1385 - remove assertion in triton attention and add an unit test
Pull Request -
State: closed - Opened by ByronHsu 9 days ago
#1384 - [Feature] Support RM API
Issue -
State: open - Opened by UbeCc 9 days ago
- 1 comment
#1383 - Rewrite mixed chunked prefill
Pull Request -
State: open - Opened by hnyls2002 9 days ago