Commits

Branch selector

main

User selector

All users

Datepicker

All time

Commit history

Commits on Aug 30, 2026

• docs: add SECURITY.md

  Show description for 4b94bdc
  jason-fxz

  authored
  4b94bdcView commit details

  Copy full SHA for 4b94bdc

  Browse repository at this point

Commits on Aug 29, 2026

• fix(kernel): avoid row-wise _scaled_mm stall on sm_89 with torch<2.12 (#243)

  Show description for 58f4b9e
  bernimccoy

  authored
  58f4b9eView commit details

  Copy full SHA for 58f4b9e

  Browse repository at this point

Commits on Aug 28, 2026

• docs(models): add Qwen3.8-Flash-Next & Qwen3.8 27b

  Show description for a05c265
  jason-fxz

  committed
  a05c265View commit details

  Copy full SHA for a05c265

  Browse repository at this point

• feat(qwen4_exp): support Qwen3.8-Flash-Next (#257)

  Show description for bd8f3d5
  jason-fxz

  authored
  bd8f3d5View commit details

  Copy full SHA for bd8f3d5

  Browse repository at this point

Commits on Aug 26, 2026

• chore(assets): update wechat group QR code

  jason-fxz

  committed
  9ef3651View commit details

  Copy full SHA for 9ef3651

  Browse repository at this point

Commits on Aug 25, 2026

• fix(fla): stop l2norm recompiling per token count

  jason-fxz

  committed
  f7c31e9View commit details

  Copy full SHA for f7c31e9

  Browse repository at this point

Commits on Aug 24, 2026

• feat(server)!: add --gpu to choose the GPU on multi-GPU machines (#117)

  Show description for 2757bb5
  jason-fxz

  authored
  2757bb5View commit details

  Copy full SHA for 2757bb5

  Browse repository at this point

• fix(checkpoint): FTW truncated shard raises OSError instead of silent garbage load (#25)

  RuixiangMa

  authored
  bd372b6View commit details

  Copy full SHA for bd372b6

  Browse repository at this point

• Merge pull request #112 from FlashML-org/feat/split-residency

  Show description for e0a3bbc
  andy-yang-1

  authored
  e0a3bbcView commit details

  Copy full SHA for e0a3bbc

  Browse repository at this point

Commits on Aug 23, 2026

• fix(moe): report the residency banks actually settle at

  jason-fxz

  committed
  831d38aView commit details

  Copy full SHA for 831d38a

  Browse repository at this point

• feat(moe): estimate expert-bank bytes from the model config

  jason-fxz

  committed
  eebb3f5View commit details

  Copy full SHA for eebb3f5

  Browse repository at this point

• feat(moe): per-layer host-bank residency -- split lock-CPU/pin-GPU layers, auto selection under capped pin quota

  jason-fxz

  committed
  c41833bView commit details

  Copy full SHA for c41833b

  Browse repository at this point

• build(kernel-cache): add sm_80 (A100/A800) to default arches (#75)

  Show description for 184a4f1
  jason-fxz

  committed
  184a4f1View commit details

  Copy full SHA for 184a4f1

  Browse repository at this point

• docs: add CONTRIBUTING.md

  jason-fxz

  committed
  f0abe58View commit details

  Copy full SHA for f0abe58

  Browse repository at this point

Commits on Aug 20, 2026

• chore(README): Add Community WeChat link to README

  Show description for 0ab982f
  andy-yang-1

  authored
  0ab982fView commit details

  Copy full SHA for 0ab982f

  Browse repository at this point

• chore(assets): Add FreeToken wechat group invite

  andy-yang-1

  authored
  bc6b269View commit details

  Copy full SHA for bc6b269

  Browse repository at this point

Commits on Aug 19, 2026

• chore(release): 0.1.2

  jason-fxz

  committed
  9db1a39View commit details

  Copy full SHA for 9db1a39

  Browse repository at this point

• docs(README): use absolute URLs so PyPI renders assets and links

  jason-fxz

  committed
  3f02e3cView commit details

  Copy full SHA for 3f02e3c

  Browse repository at this point

• Merge branch 'dev/refine-readme': README overhaul + quick start guide

  jason-fxz

  committed
  c0a4a60View commit details

  Copy full SHA for c0a4a60

  Browse repository at this point

• docs(README): add a Desktop screenshot to Getting Started

  Show description for 9ecbc9f
  jason-fxz

  committed
  9ecbc9fView commit details

  Copy full SHA for 9ecbc9f

  Browse repository at this point

• feat(stats): record per-request TTFT and report its mean

  Show description for 12ed695
  jason-fxz

  committed
  12ed695View commit details

  Copy full SHA for 12ed695

  Browse repository at this point

• perf(fp8): run per-tensor fp8 as W8A8 via scaled_mm (#7)

  jason-fxz

  authored
  586a6c1View commit details

  Copy full SHA for 586a6c1

  Browse repository at this point

Commits on Aug 18, 2026

• docs(README): add install commands to Getting Started

  jason-fxz

  committed
  f4373f8View commit details

  Copy full SHA for f4373f8

  Browse repository at this point

• docs(README): add Citation

  jason-fxz

  committed
  5528af0View commit details

  Copy full SHA for 5528af0

  Browse repository at this point

• docs: refine README.md, add quick start guide

  Show description for fca2758
  jason-fxz

  committed
  fca2758View commit details

  Copy full SHA for fca2758

  Browse repository at this point

• chore(README.md): add links.

  jason-fxz

  authored
  5812fbdView commit details

  Copy full SHA for 5812fbd

  Browse repository at this point

• Support muse glimmer (#4)

  Show description for 6223cda
  andy-yang-1

  authored
  6223cdaView commit details

  Copy full SHA for 6223cda

  Browse repository at this point

• build(release): pypi-ready wheels, metadata, and publish workflow (#6)

  jason-fxz

  authored
  b86a904View commit details

  Copy full SHA for b86a904

  Browse repository at this point

• build(release): pypi-ready wheels, metadata, and publish workflow

  jason-fxz

  committed
  76edc16View commit details

  Copy full SHA for 76edc16

  Browse repository at this point

Commits on Aug 16, 2026

• fix(server): stop API server when backend dies

  Show description for 711325d
  jason-fxz

  committed
  711325dView commit details

  Copy full SHA for 711325d

  Browse repository at this point

• ci: move nightly wheels to 11:00 UTC

  jason-fxz

  committed
  2635246View commit details

  Copy full SHA for 2635246

  Browse repository at this point

• [Feature] unify reasoning effort on one shared scale (#5)

  Show description for d7cd6ed
  jason-fxz

  authored
  d7cd6edView commit details

  Copy full SHA for d7cd6ed

  Browse repository at this point

Commits on Aug 15, 2026

• feat(launch): support launch deepseek harness (#3)

  Show description for a257208
  jason-fxz

  authored
  a257208View commit details

  Copy full SHA for a257208

  Browse repository at this point

Commits on Aug 14, 2026

• feat(server): enable reasoning_effort on /v1/chat/completions (#2)

  Show description for 4f510f1
  jason-fxz

  authored
  4f510f1View commit details

  Copy full SHA for 4f510f1

  Browse repository at this point

• chore(assets): update icons & logos

  jason-fxz

  committed
  c28e93aView commit details

  Copy full SHA for c28e93a

  Browse repository at this point