Reposen Monogram
Reposenreposen.se
/llm.txtGitHub Repo
sgl-project icon

sgl-project/sglang

v0.5.23

Curated ai tools / local-ai / runtime repository (sgl-project/sglang) tracked via conditional GitHub .atom polling.

BREAKING
What is sgl-project/sglang?

SGLang is a high-performance serving framework for large language models and diffusion models, designed to maximize throughput and minimize latency through advanced Radix Attention, tensor parallelism, and custom kernel fusions. It addresses the high compute costs and memory bottlenecks of modern generative AI inference by optimizing KV caching and memory layouts across hardware accelerators.

RUNTIMEpypi:sglangPythonreleases.atom
38,831+58 stars (24h)
#local-ai#sglang
AI Executive Summary & Artifact Size Impact
Quick Summary: What Changed · What To Do · Upgrade Effort

Upgrade DeepSeek-V4 chat encoding and default SWA bounded replay. Update API configurations. Migration: Moderate.

Semver: MINOR·Manifest: pyproject.toml
Artifact Size Impactunavailable
Size Unavailable
Telemetry unmeasured for pre-release or source-only registry build
Breaking Changes, Release Highlights & Migration Snippet

Key Release Highlights (v0.5.23)

  • DeepSeek-V4 and DeepSeek-V4.1 chat API requests now route through official deepseek-recipe encoding.
  • Enabled DeepSeek-V4.1 decoder SWA bounded replay by default, reducing first-token latency.
  • Removed the deprecated tokenspeed_mla attention backend and --speculative-skip-dp-mlp-sync flag.
  • Dropped unsafe weights_only=False pickle loading support for legacy .pt model checkpoints.

Breaking Changes (Action Required)

  • DeepSeek-V4/V4.1 chat requests now use deepseek-recipe; custom encoding_dsv4.py endpoints are removed.
  • Numeric reasoning_effort on V4 inputs returns a 400 error.
  • The tokenspeed_mla attention backend and --speculative-skip-dp-mlp-sync flag are completely removed.
  • Unsafe pickle fallback (weights_only=False) for .pt checkpoints is disabled.
Copy-Paste Upgrade / Migration Snippet
uv pip install --prerelease=allow sglang==0.5.23

Ecosystem Compatibility Matrix & Verified Graph Warnings

Python >=3.10compatible— Requires Python runtime compatibility for underlying server and plugin bindings.
PyTorch >=2.5compatible— Required for native tensor operations, custom operators, and compiled CUDA graphs.

Zero-Noise Historical Release Timeline (1)

Format: [Core Change] + [Required Action] + [Migration Effort]
v0.5.23BREAKING⚖️ Size Unavailable

Upgrade DeepSeek-V4 chat encoding and default SWA bounded replay. Update API configurations. Migration: Moderate.

Upgrade & Migration Q&A (sgl-project/sglang v0.5.23)

Direct Answers for Engineers & AI Agents

Is sgl-project/sglang v0.5.23 safe to upgrade in production?

sgl-project/sglang v0.5.23 is classified as BREAKING (MINOR release). Upgrade DeepSeek-V4 chat encoding and default SWA bounded replay. Update API configurations. Migration: Moderate.

What breaking changes or compatibility risks exist in sgl-project/sglang v0.5.23?

DeepSeek-V4/V4.1 chat requests now use deepseek-recipe; custom encoding_dsv4.py endpoints are removed. Numeric reasoning_effort on V4 inputs returns a 400 error. The tokenspeed_mla attention backend and --speculative-skip-dp-mlp-sync flag are completely removed. Unsafe pickle fallback (weights_only=False) for .pt checkpoints is disabled.

What is the bundle size impact of sglang v0.5.23?

Measured bundle size telemetry is currently unavailable for sglang v0.5.23; verify build output locally before deploying.

How do I upgrade sglang to v0.5.23?

Upgrade sglang to v0.5.23 by running "pip install sglang==0.5.23" and applying the migration steps: uv pip install --prerelease=allow sglang==0.5.23