electron-rare/exo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix Nemotron cache leak upstream (#1819)

Browse Source 
## Motivation
Nemotron Cascade and Nano failing at long decodes.

## Changes

Fixed upstream, just change pyproject and uv lock here.


## Test Plan
### Automated Testing
Tested with a reproduce script upstream
This commit is contained in:
rltakashige
2026-03-30 17:53:21 +01:00
committed by GitHub
parent c6815bfdce
commit d9ed943034
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pyproject.toml
+1 -1
View File
@@ -63,7 +63,7 @@ members = ["rust/exo_pyo3_bindings", "bench"]
[tool.uv.sources]
exo_pyo3_bindings = { workspace = true }
mlx = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git", branch = "address-rdma-gpu-locks", marker = "sys_platform == 'darwin'" }
mlx-lm = { git = "https://github.com/rltakashige/mlx-lm", branch = "leo/fix-deepseek-v32-indexer" }
mlx-lm = { git = "https://github.com/rltakashige/mlx-lm", branch = "leo/fix-arrayscache-leak" }
# Uncomment to use local mlx/mlx-lm development versions:
# mlx = { path = "/Users/Shared/mlx", editable=true }
# mlx-lm = { path = "/Users/Shared/mlx-lm", editable=true }
uv.lock
Generated
+2 -2
View File
@@ -599,7 +599,7 @@ requires-dist = [
{ name = "mflux", specifier = "==0.17.2" },
{ name = "mlx", marker = "sys_platform == 'darwin'", git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks" },
{ name = "mlx", extras = ["cpu"], marker = "sys_platform == 'linux'", specifier = "==0.30.6" },
{ name = "mlx-lm", git = "https://github.com/rltakashige/mlx-lm?branch=leo%2Ffix-deepseek-v32-indexer" },
{ name = "mlx-lm", git = "https://github.com/rltakashige/mlx-lm?branch=leo%2Ffix-arrayscache-leak" },
{ name = "mlx-vlm", specifier = ">=0.3.11" },
{ name = "msgspec", specifier = ">=0.19.0" },
{ name = "openai-harmony", specifier = ">=0.0.8" },
@@ -1528,7 +1528,7 @@ wheels = [
[[package]]
name = "mlx-lm"
version = "0.31.2"
source = { git = "https://github.com/rltakashige/mlx-lm?branch=leo%2Ffix-deepseek-v32-indexer#d388ff77858fec3b5d2e3b1d9502a7e2878b8109" }
source = { git = "https://github.com/rltakashige/mlx-lm?branch=leo%2Ffix-arrayscache-leak#d36e9b661e55a5fc0f77fb6f17ea643aa2dc87aa" }
dependencies = [
{ name = "jinja2", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "mlx", version = "0.31.2.dev20260324+e5e64331", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#e5e64331830d9b04ae9082b843073f9c1fa7705e" }, marker = "sys_platform == 'darwin'" },