Skip to content

Instantly share code, notes, and snippets.

View eshelman's full-sized avatar

Eliot Eshelman eshelman

View GitHub Profile
#!/usr/bin/env bash
#
# run_nim.sh — ergonomic launcher for NVIDIA NIM LLM containers
#
# Usage examples are at the bottom of --help.
#
set -euo pipefail
# ---------- defaults ----------
HOST_PORT=8000 # what you hit from your browser/curl
@eshelman
eshelman / test.txt
Created July 3, 2018 13:34
test123
This is just a test
@eshelman
eshelman / test.txt
Created July 3, 2018 13:33
test123
This is just a test
@eshelman
eshelman / test.txt
Created July 3, 2018 13:28
test123
This is just a test
@eshelman
eshelman / test.txt
Created July 2, 2018 22:02
test123
This is just a test
@eshelman
eshelman / test.txt
Created July 2, 2018 21:59
test123
This is just a test
@eshelman
eshelman / latency.txt
Last active January 20, 2026 07:44 — forked from jboner/latency.txt
HPC-oriented Latency Numbers Every Programmer Should Know
Latency Comparison Numbers
--------------------------
L1 cache reference/hit 1.5 ns 4 cycles
Floating-point add/mult/FMA operation 1.5 ns 4 cycles
L2 cache reference/hit 5 ns 12 ~ 17 cycles
Branch mispredict 6 ns 15 ~ 20 cycles
L3 cache hit (unshared cache line) 16 ns 42 cycles
L3 cache hit (shared line in another core) 25 ns 65 cycles
Mutex lock/unlock 25 ns
L3 cache hit (modified in another core) 29 ns 75 cycles
### Keybase proof
I hereby claim:
* I am eshelman on github.
* I am eshelman (https://keybase.io/eshelman) on keybase.
* I have a public key whose fingerprint is 7845 15B9 5064 6596 9B40 A5F3 7699 60DE F83D CCEE
To claim this, I am signing this object:
@eshelman
eshelman / iostat_log_from_overloaded_node
Created May 12, 2015 17:43
Comparison of "healthy" and "overloaded" storage systems
Linux 2.6.32-431.23.3.el6.x86_64 (dirac2) 03/17/2015 _x86_64_ (80 CPU)
Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await svctm %util
sdc 1.00 915.00 106.67 61.67 21349.33 3666.67 297.22 16.40 95.49 4.10 68.97
sdd 2.67 898.67 47.67 73.33 7954.67 3552.00 190.19 13.28 104.28 2.94 35.53
sdb 0.67 1007.33 56.00 67.67 12902.67 4068.00 274.46 14.61 115.84 3.26 40.37
sdf 0.00 929.67 35.00 74.67 4972.00 4017.33 163.94 5.25 47.84 2.10 23.00
sde 1.33 934.33 125.00 67.00 21518.67 3797.33 263.71 27.20 138.66 3.94 75.63
sda 0.00 1007.33 86.00 67.67 13326.67 4068.00 226.39 10.97 67.86 2.85 43.87
md1 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00