René's URL Explorer Experiment

Title: History for examples/quantize/quantize.cpp - Exploder98/llama.cpp · GitHub

Open Graph Title: History for examples/quantize/quantize.cpp - Exploder98/llama.cpp

X Title: History for examples/quantize/quantize.cpp - Exploder98/llama.cpp

Description: LLM inference in C/C++. Contribute to Exploder98/llama.cpp development by creating an account on GitHub.

Open Graph Description: LLM inference in C/C++. Contribute to Exploder98/llama.cpp development by creating an account on GitHub.

X Description: LLM inference in C/C++. Contribute to Exploder98/llama.cpp development by creating an account on GitHub.

Opengraph URL: https://github.com/Exploder98/llama.cpp

X: @github

direct link

Domain: github.com

route-pattern	/:user_id/:repository/commits(/*name)
route-controller	commits
route-action	show
fetch-nonce	v2:60192cdf-5a0a-08fc-fb30-635fbb4019f5
current-catalog-service-hash	f3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-id	8F1E:397AD8:60A85CB:87C1C8F:6A500010
html-safe-nonce	6982c4e995774c8d06d572f55c0a54bbcf09271c6fabd372bfaaa3db9ed54db0
visitor-payload	eyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiI4RjFFOjM5N0FEODo2MEE4NUNCOjg3QzFDOEY6NkE1MDAwMTAiLCJ2aXNpdG9yX2lkIjoiNjMxMTA0Mjk4OTY4MzYzODI4OSIsInJlZ2lvbl9lZGdlIjoiaWFkIiwicmVnaW9uX3JlbmRlciI6ImlhZCJ9
visitor-hmac	72857c139b1d7293317f563f82559684bb19a1bf52869886c7d58853a84fd5ea
hovercard-subject-tag	repository:837848890
github-keyboard-shortcuts	repository,copilot
google-site-verification	Apib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-url	https://collector.github.com/github/collect
analytics-location	///commits/show
fb:app_id	1401488693436528
apple-itunes-app	app-id=1477376905, app-argument=https://github.com/Exploder98/llama.cpp/commits/master/examples/quantize/quantize.cpp
twitter:image	https://opengraph.githubassets.com/afecbd450b3f06a4a3a24d6bf58c817385baf0586647e7bb9053e3671625719d/Exploder98/llama.cpp
twitter:card	summary_large_image
og:image	https://opengraph.githubassets.com/afecbd450b3f06a4a3a24d6bf58c817385baf0586647e7bb9053e3671625719d/Exploder98/llama.cpp
og:image:alt	LLM inference in C/C++. Contribute to Exploder98/llama.cpp development by creating an account on GitHub.
og:image:width	1200
og:image:height	600
og:site_name	GitHub
og:type	object
hostname	github.com
expected-hostname	github.com
None	56eec25a3430492dd6ec2a480eb33256a0da5192d5714b0db4f5ab5f33203d94
turbo-cache-control	no-cache
go-import	github.com/Exploder98/llama.cpp git https://github.com/Exploder98/llama.cpp.git
octolytics-dimension-user_id	22271977
octolytics-dimension-user_login	Exploder98
octolytics-dimension-repository_id	837848890
octolytics-dimension-repository_nwo	Exploder98/llama.cpp
octolytics-dimension-repository_public	true
octolytics-dimension-repository_is_fork	true
octolytics-dimension-repository_parent_id	612354784
octolytics-dimension-repository_parent_nwo	ggml-org/llama.cpp
octolytics-dimension-repository_network_root_id	612354784
octolytics-dimension-repository_network_root_nwo	ggml-org/llama.cpp
turbo-body-classes	logged-out env-production page-responsive
disable-turbo	false
browser-stats-url	https://api.github.com/_private/browser/stats
browser-errors-url	https://api.github.com/_private/browser/errors
release	e155b8a71f9284454f73118dfe5e634e74f7afb3
ui-target	full
theme-color	#1e2327
color-scheme	light dark

Links:

Skip to content	https://github.com/Exploder98/llama.cpp/commits/master/examples/quantize/quantize.cpp#start-of-content
	https://github.com/
Sign in	https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FExploder98%2Fllama.cpp%2Fcommits%2Fmaster%2Fexamples%2Fquantize%2Fquantize.cpp
GitHub CopilotWrite better code with AI	https://github.com/features/copilot
GitHub Copilot appDirect agents from issue to merge	https://github.com/features/ai/github-app
MCP RegistryNewIntegrate external tools	https://github.com/mcp
ActionsAutomate any workflow	https://github.com/features/actions
CodespacesInstant dev environments	https://github.com/features/codespaces
IssuesPlan and track work	https://github.com/features/issues
Code ReviewManage code changes	https://github.com/features/code-review
GitHub Advanced SecurityFind and fix vulnerabilities	https://github.com/security/advanced-security
Code securitySecure your code as you build	https://github.com/security/advanced-security/code-security
Secret protectionStop leaks before they start	https://github.com/security/advanced-security/secret-protection
Why GitHub	https://github.com/why-github
Documentation	https://docs.github.com
Blog	https://github.blog
Changelog	https://github.blog/changelog
Marketplace	https://github.com/marketplace
View all features	https://github.com/features
Enterprises	https://github.com/enterprise
Small and medium teams	https://github.com/team
Startups	https://github.com/enterprise/startups
Nonprofits	https://github.com/solutions/industry/nonprofits
App Modernization	https://github.com/solutions/use-case/app-modernization
DevSecOps	https://github.com/solutions/use-case/devsecops
DevOps	https://github.com/solutions/use-case/devops
CI/CD	https://github.com/solutions/use-case/ci-cd
View all use cases	https://github.com/solutions/use-case
Healthcare	https://github.com/solutions/industry/healthcare
Financial services	https://github.com/solutions/industry/financial-services
Manufacturing	https://github.com/solutions/industry/manufacturing
Government	https://github.com/solutions/industry/government
View all industries	https://github.com/solutions/industry
View all solutions	https://github.com/solutions
AI	https://github.com/resources/articles?topic=ai
Software Development	https://github.com/resources/articles?topic=software-development
DevOps	https://github.com/resources/articles?topic=devops
Security	https://github.com/resources/articles?topic=security
View all topics	https://github.com/resources/articles
Customer stories	https://github.com/customer-stories
Events & webinars	https://github.com/resources/events
Ebooks & reports	https://github.com/resources/whitepapers
Business insights	https://github.com/solutions/executive-insights
GitHub Skills	https://skills.github.com
Documentation	https://docs.github.com
Customer support	https://support.github.com
Community forum	https://github.com/orgs/community/discussions
Trust center	https://github.com/trust-center
Partners	https://github.com/partners
View all resources	https://github.com/resources
GitHub SponsorsFund open source developers	https://github.com/open-source/sponsors
Security Lab	https://securitylab.github.com
Maintainer Community	https://maintainers.github.com
Accelerator	https://github.com/open-source/accelerator
GitHub Stars	https://stars.github.com
Archive Program	https://archiveprogram.github.com
Topics	https://github.com/topics
Trending	https://github.com/trending
Collections	https://github.com/collections
Enterprise platformAI-powered developer platform	https://github.com/enterprise
GitHub Advanced SecurityEnterprise-grade security features	https://github.com/security/advanced-security
Copilot for BusinessEnterprise-grade AI features	https://github.com/features/copilot/copilot-business
Premium SupportEnterprise-grade 24/7 support	https://github.com/enterprise/premium-support
Pricing	https://github.com/pricing
Search syntax tips	https://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
documentation	https://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
Sign in	https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FExploder98%2Fllama.cpp%2Fcommits%2Fmaster%2Fexamples%2Fquantize%2Fquantize.cpp
Sign up	https://github.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E%2Fcommits%2Fshow&source=header-repo&source_repo=Exploder98%2Fllama.cpp
Reload	https://github.com/Exploder98/llama.cpp/commits/master/examples/quantize/quantize.cpp
Reload	https://github.com/Exploder98/llama.cpp/commits/master/examples/quantize/quantize.cpp
Reload	https://github.com/Exploder98/llama.cpp/commits/master/examples/quantize/quantize.cpp
Exploder98	https://github.com/Exploder98
llama.cpp	https://github.com/Exploder98/llama.cpp
ggml-org/llama.cpp	https://github.com/ggml-org/llama.cpp
Notifications	https://github.com/login?return_to=%2FExploder98%2Fllama.cpp
Fork 0	https://github.com/login?return_to=%2FExploder98%2Fllama.cpp
Star 0	https://github.com/login?return_to=%2FExploder98%2Fllama.cpp
Code	https://github.com/Exploder98/llama.cpp
Pull requests 0	https://github.com/Exploder98/llama.cpp/pulls
Actions	https://github.com/Exploder98/llama.cpp/actions
Projects	https://github.com/Exploder98/llama.cpp/projects
Security and quality 0	https://github.com/Exploder98/llama.cpp/security
Insights	https://github.com/Exploder98/llama.cpp/pulse
Code	https://github.com/Exploder98/llama.cpp
Pull requests	https://github.com/Exploder98/llama.cpp/pulls
Actions	https://github.com/Exploder98/llama.cpp/actions
Projects	https://github.com/Exploder98/llama.cpp/projects
Security and quality	https://github.com/Exploder98/llama.cpp/security
Insights	https://github.com/Exploder98/llama.cpp/pulse
llama.cpp	https://github.com/Exploder98/llama.cpp/commits
examples	https://github.com/Exploder98/llama.cpp/commits/master/examples
quantize	https://github.com/Exploder98/llama.cpp/commits/master/examples/quantize
quantize.cpp	https://github.com/Exploder98/llama.cpp/commits/master/examples/quantize/quantize.cpp
master	https://github.com/Exploder98/llama.cpp/tree/master
llama : valign + remove unused ftype (#8502)	https://github.com/Exploder98/llama.cpp/commit/0efec57787cb8d8d76b17cd3765e6521e22c1f19
	https://github.com/ggerganov
ggerganov	https://github.com/Exploder98/llama.cpp/commits?author=ggerganov
0efec57	https://github.com/Exploder98/llama.cpp/commit/0efec57787cb8d8d76b17cd3765e6521e22c1f19
	https://github.com/Exploder98/llama.cpp/blob/0efec57787cb8d8d76b17cd3765e6521e22c1f19/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/0efec57787cb8d8d76b17cd3765e6521e22c1f19
ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (#5780)	https://github.com/Exploder98/llama.cpp/commit/0f1a39f3439825acf7e3a1663566d410be152170
	https://github.com/Dibakar
Dibakar	https://github.com/Exploder98/llama.cpp/commits?author=Dibakar
0f1a39f	https://github.com/Exploder98/llama.cpp/commit/0f1a39f3439825acf7e3a1663566d410be152170
	https://github.com/Exploder98/llama.cpp/blob/0f1a39f3439825acf7e3a1663566d410be152170/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/0f1a39f3439825acf7e3a1663566d410be152170
Update llama-quantize ppl/file size output from LLaMA-v1 to Llama-3 values (#8058)	https://github.com/Exploder98/llama.cpp/commit/5b48cd53a87928db0c6447f0c9dac4db5802102d
	https://github.com/ddh0
ddh0	https://github.com/Exploder98/llama.cpp/commits?author=ddh0
5b48cd5	https://github.com/Exploder98/llama.cpp/commit/5b48cd53a87928db0c6447f0c9dac4db5802102d
	https://github.com/Exploder98/llama.cpp/blob/5b48cd53a87928db0c6447f0c9dac4db5802102d/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/5b48cd53a87928db0c6447f0c9dac4db5802102d
common : normalize naming style (#7462)	https://github.com/Exploder98/llama.cpp/commit/6ff13987ad1a9519bee13dd98b6a21cd98979aab
	https://github.com/ggerganov
ggerganov	https://github.com/Exploder98/llama.cpp/commits?author=ggerganov
6ff1398	https://github.com/Exploder98/llama.cpp/commit/6ff13987ad1a9519bee13dd98b6a21cd98979aab
	https://github.com/Exploder98/llama.cpp/blob/6ff13987ad1a9519bee13dd98b6a21cd98979aab/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/6ff13987ad1a9519bee13dd98b6a21cd98979aab
quantize : fix --keep-split check (#7374)	https://github.com/Exploder98/llama.cpp/commit/1ea2a0036e88172d6c8bf7e1a1989a03894dc955
	https://github.com/fredlas
fredlas	https://github.com/Exploder98/llama.cpp/commits?author=fredlas
1ea2a00	https://github.com/Exploder98/llama.cpp/commit/1ea2a0036e88172d6c8bf7e1a1989a03894dc955
	https://github.com/Exploder98/llama.cpp/blob/1ea2a0036e88172d6c8bf7e1a1989a03894dc955/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/1ea2a0036e88172d6c8bf7e1a1989a03894dc955
ggml : introduce bfloat16 support (#6412)	https://github.com/Exploder98/llama.cpp/commit/3855416027cb25d9a708ffa5581cf503a87856a6
	https://github.com/jart
jart	https://github.com/Exploder98/llama.cpp/commits?author=jart
3855416	https://github.com/Exploder98/llama.cpp/commit/3855416027cb25d9a708ffa5581cf503a87856a6
	https://github.com/Exploder98/llama.cpp/blob/3855416027cb25d9a708ffa5581cf503a87856a6/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/3855416027cb25d9a708ffa5581cf503a87856a6
quantize: add imatrix and dataset metadata in GGUF (#6658)	https://github.com/Exploder98/llama.cpp/commit/0c4d489e29e53589bf13a801fe7c94b7b546d8f6
0c4d489	https://github.com/Exploder98/llama.cpp/commit/0c4d489e29e53589bf13a801fe7c94b7b546d8f6
	https://github.com/Exploder98/llama.cpp/blob/0c4d489e29e53589bf13a801fe7c94b7b546d8f6/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/0c4d489e29e53589bf13a801fe7c94b7b546d8f6
quantize : add '--keep-split' to quantize model into shards (#6688)	https://github.com/Exploder98/llama.cpp/commit/1966eb2615242f224bf9ca939db8905ab6a174a0
1966eb2	https://github.com/Exploder98/llama.cpp/commit/1966eb2615242f224bf9ca939db8905ab6a174a0
	https://github.com/Exploder98/llama.cpp/blob/1966eb2615242f224bf9ca939db8905ab6a174a0/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/1966eb2615242f224bf9ca939db8905ab6a174a0
ggml : mul_mat_id use the same tensor for all the experts (#6387)	https://github.com/Exploder98/llama.cpp/commit/08a0c0206075556e82aca0feafad530dcc5f1426
slaren	https://github.com/Exploder98/llama.cpp/commits?author=slaren
ggerganov	https://github.com/Exploder98/llama.cpp/commits?author=ggerganov
08a0c02	https://github.com/Exploder98/llama.cpp/commit/08a0c0206075556e82aca0feafad530dcc5f1426
	https://github.com/Exploder98/llama.cpp/blob/08a0c0206075556e82aca0feafad530dcc5f1426/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/08a0c0206075556e82aca0feafad530dcc5f1426
IQ1_M: 1.75 bpw quantization (#6302)	https://github.com/Exploder98/llama.cpp/commit/55c1b2a3bbd470e9e2a3a0618b92cf64a885f806
ikawrakow	https://github.com/Exploder98/llama.cpp/commits?author=ikawrakow
55c1b2a	https://github.com/Exploder98/llama.cpp/commit/55c1b2a3bbd470e9e2a3a0618b92cf64a885f806
	https://github.com/Exploder98/llama.cpp/blob/55c1b2a3bbd470e9e2a3a0618b92cf64a885f806/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/55c1b2a3bbd470e9e2a3a0618b92cf64a885f806
quantize : be able to override metadata by key (#6321)	https://github.com/Exploder98/llama.cpp/commit/d25b1c31b07c3675443a55a828dd58cfef5a241c
d25b1c3	https://github.com/Exploder98/llama.cpp/commit/d25b1c31b07c3675443a55a828dd58cfef5a241c
	https://github.com/Exploder98/llama.cpp/blob/d25b1c31b07c3675443a55a828dd58cfef5a241c/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/d25b1c31b07c3675443a55a828dd58cfef5a241c
quantize: options for output and token embedding tensors qtype (#6239)	https://github.com/Exploder98/llama.cpp/commit/1d0331c12a2f2a6296b471232bd4e66fbf06e6a1
ikawrakow	https://github.com/Exploder98/llama.cpp/commits?author=ikawrakow
1d0331c	https://github.com/Exploder98/llama.cpp/commit/1d0331c12a2f2a6296b471232bd4e66fbf06e6a1
	https://github.com/Exploder98/llama.cpp/blob/1d0331c12a2f2a6296b471232bd4e66fbf06e6a1/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/1d0331c12a2f2a6296b471232bd4e66fbf06e6a1
IQ4_XS: a 4.25 bpw quantization (#5747)	https://github.com/Exploder98/llama.cpp/commit/0becb22ac05b6542bd9d5f2235691aa1d3d4d307
ikawrakow	https://github.com/Exploder98/llama.cpp/commits?author=ikawrakow
0becb22	https://github.com/Exploder98/llama.cpp/commit/0becb22ac05b6542bd9d5f2235691aa1d3d4d307
	https://github.com/Exploder98/llama.cpp/blob/0becb22ac05b6542bd9d5f2235691aa1d3d4d307/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/0becb22ac05b6542bd9d5f2235691aa1d3d4d307
Adding IQ2_S and IQ2_M to complete coverage of the 2-3 bit quantization range (#5721)	https://github.com/Exploder98/llama.cpp/commit/a33e6a0d2a66104ea9a906bdbf8a94d050189d91
a33e6a0	https://github.com/Exploder98/llama.cpp/commit/a33e6a0d2a66104ea9a906bdbf8a94d050189d91
	https://github.com/Exploder98/llama.cpp/blob/a33e6a0d2a66104ea9a906bdbf8a94d050189d91/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/a33e6a0d2a66104ea9a906bdbf8a94d050189d91
IQ3_S: a much better alternative to Q3_K (#5676)	https://github.com/Exploder98/llama.cpp/commit/4c4cb30736582cacb1a164a9d4bc8e17b1014be7
ikawrakow	https://github.com/Exploder98/llama.cpp/commits?author=ikawrakow
4c4cb30	https://github.com/Exploder98/llama.cpp/commit/4c4cb30736582cacb1a164a9d4bc8e17b1014be7
	https://github.com/Exploder98/llama.cpp/blob/4c4cb30736582cacb1a164a9d4bc8e17b1014be7/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/4c4cb30736582cacb1a164a9d4bc8e17b1014be7
IQ4_NL: 4-bit non-linear quants with blocks of 32 (#5590)	https://github.com/Exploder98/llama.cpp/commit/a14679cc30c785e75d38028bae6ec39c6209ddef
ikawrakow	https://github.com/Exploder98/llama.cpp/commits?author=ikawrakow
a14679c	https://github.com/Exploder98/llama.cpp/commit/a14679cc30c785e75d38028bae6ec39c6209ddef
	https://github.com/Exploder98/llama.cpp/blob/a14679cc30c785e75d38028bae6ec39c6209ddef/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/a14679cc30c785e75d38028bae6ec39c6209ddef
1.5 bit quantization (#5453)	https://github.com/Exploder98/llama.cpp/commit/bd2d4e393b2b7d2a1b2e201058e26017c9728ead
ikawrakow	https://github.com/Exploder98/llama.cpp/commits?author=ikawrakow
bd2d4e3	https://github.com/Exploder98/llama.cpp/commit/bd2d4e393b2b7d2a1b2e201058e26017c9728ead
	https://github.com/Exploder98/llama.cpp/blob/bd2d4e393b2b7d2a1b2e201058e26017c9728ead/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/bd2d4e393b2b7d2a1b2e201058e26017c9728ead
ggml : add numa options (#5377)	https://github.com/Exploder98/llama.cpp/commit/f486f6e1e5e9d01603d9325ab3e05f1edb362a95
f486f6e	https://github.com/Exploder98/llama.cpp/commit/f486f6e1e5e9d01603d9325ab3e05f1edb362a95
	https://github.com/Exploder98/llama.cpp/blob/f486f6e1e5e9d01603d9325ab3e05f1edb362a95/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/f486f6e1e5e9d01603d9325ab3e05f1edb362a95
refactor : switch to emplace_back to avoid extra object (#5291)	https://github.com/Exploder98/llama.cpp/commit/52bb63c7082c859c3f1dfc527227e6a95b299c7c
	https://github.com/MKlimenko
MKlimenko	https://github.com/Exploder98/llama.cpp/commits?author=MKlimenko
52bb63c	https://github.com/Exploder98/llama.cpp/commit/52bb63c7082c859c3f1dfc527227e6a95b299c7c
	https://github.com/Exploder98/llama.cpp/blob/52bb63c7082c859c3f1dfc527227e6a95b299c7c/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/52bb63c7082c859c3f1dfc527227e6a95b299c7c
SOTA 3-bit quants (#5196)	https://github.com/Exploder98/llama.cpp/commit/f4d7e5497485ce6ce0e322533930b7da4657dd2d
ikawrakow	https://github.com/Exploder98/llama.cpp/commits?author=ikawrakow
f4d7e54	https://github.com/Exploder98/llama.cpp/commit/f4d7e5497485ce6ce0e322533930b7da4657dd2d
	https://github.com/Exploder98/llama.cpp/blob/f4d7e5497485ce6ce0e322533930b7da4657dd2d/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/f4d7e5497485ce6ce0e322533930b7da4657dd2d
quantize : fix typo (#5211)	https://github.com/Exploder98/llama.cpp/commit/7359016c7c0f65dc30cf79791212b06f15866450
	https://github.com/first-leon
first-leon	https://github.com/Exploder98/llama.cpp/commits?author=first-leon
7359016	https://github.com/Exploder98/llama.cpp/commit/7359016c7c0f65dc30cf79791212b06f15866450
	https://github.com/Exploder98/llama.cpp/blob/7359016c7c0f65dc30cf79791212b06f15866450/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/7359016c7c0f65dc30cf79791212b06f15866450
llama : add Q3_K_XS (#5060)	https://github.com/Exploder98/llama.cpp/commit/66d575c45c5a370d668f9c3283cdf348e2329fa2
ikawrakow	https://github.com/Exploder98/llama.cpp/commits?author=ikawrakow
66d575c	https://github.com/Exploder98/llama.cpp/commit/66d575c45c5a370d668f9c3283cdf348e2329fa2
	https://github.com/Exploder98/llama.cpp/blob/66d575c45c5a370d668f9c3283cdf348e2329fa2/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/66d575c45c5a370d668f9c3283cdf348e2329fa2
Add ability to use importance matrix for all k-quants (#4930)	https://github.com/Exploder98/llama.cpp/commit/467a882fd2e5b6172897b49aa45aa29bd3f27685
ikawrakow	https://github.com/Exploder98/llama.cpp/commits?author=ikawrakow
467a882	https://github.com/Exploder98/llama.cpp/commit/467a882fd2e5b6172897b49aa45aa29bd3f27685
	https://github.com/Exploder98/llama.cpp/blob/467a882fd2e5b6172897b49aa45aa29bd3f27685/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/467a882fd2e5b6172897b49aa45aa29bd3f27685
2-bit quantizations (#4897)	https://github.com/Exploder98/llama.cpp/commit/147b17ac94a24d524e367cda26a9ff6245689f34
ikawrakow	https://github.com/Exploder98/llama.cpp/commits?author=ikawrakow
147b17a	https://github.com/Exploder98/llama.cpp/commit/147b17ac94a24d524e367cda26a9ff6245689f34
	https://github.com/Exploder98/llama.cpp/blob/147b17ac94a24d524e367cda26a9ff6245689f34/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/147b17ac94a24d524e367cda26a9ff6245689f34
llama : restore intended k-quants mixes for MoE models (#4872)	https://github.com/Exploder98/llama.cpp/commit/469e75d0a35b08de549a4fd87f082ca7a8a539ba
469e75d	https://github.com/Exploder98/llama.cpp/commit/469e75d0a35b08de549a4fd87f082ca7a8a539ba
	https://github.com/Exploder98/llama.cpp/blob/469e75d0a35b08de549a4fd87f082ca7a8a539ba/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/469e75d0a35b08de549a4fd87f082ca7a8a539ba
build : link against build info instead of compiling against it (#3879)	https://github.com/Exploder98/llama.cpp/commit/b12fa0d1c13596869c512f49a526b979c94787cc
cebtenzzre	https://github.com/Exploder98/llama.cpp/commits?author=cebtenzzre
kassane	https://github.com/Exploder98/llama.cpp/commits?author=kassane
b12fa0d	https://github.com/Exploder98/llama.cpp/commit/b12fa0d1c13596869c512f49a526b979c94787cc
	https://github.com/Exploder98/llama.cpp/blob/b12fa0d1c13596869c512f49a526b979c94787cc/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/b12fa0d1c13596869c512f49a526b979c94787cc
ggml : quantization refactoring (#3833)	https://github.com/Exploder98/llama.cpp/commit/d69d777c02b9ac405a95f3cbfba219a990caefff
ggerganov	https://github.com/Exploder98/llama.cpp/commits?author=ggerganov
cebtenzzre	https://github.com/Exploder98/llama.cpp/commits?author=cebtenzzre
d69d777	https://github.com/Exploder98/llama.cpp/commit/d69d777c02b9ac405a95f3cbfba219a990caefff
	https://github.com/Exploder98/llama.cpp/blob/d69d777c02b9ac405a95f3cbfba219a990caefff/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/d69d777c02b9ac405a95f3cbfba219a990caefff
build : enable more non-default compiler warnings (#3200)	https://github.com/Exploder98/llama.cpp/commit/bc39553c901a91cfcb757863586250838c83eeab
	https://github.com/cebtenzzre
cebtenzzre	https://github.com/Exploder98/llama.cpp/commits?author=cebtenzzre
bc39553	https://github.com/Exploder98/llama.cpp/commit/bc39553c901a91cfcb757863586250838c83eeab
	https://github.com/Exploder98/llama.cpp/blob/bc39553c901a91cfcb757863586250838c83eeab/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/bc39553c901a91cfcb757863586250838c83eeab
make : restore build-info.h dependency for several targets (#3205)	https://github.com/Exploder98/llama.cpp/commit/8781013ef654270cbead3e0011e33a6d690fb168
	https://github.com/cebtenzzre
cebtenzzre	https://github.com/Exploder98/llama.cpp/commits?author=cebtenzzre
8781013	https://github.com/Exploder98/llama.cpp/commit/8781013ef654270cbead3e0011e33a6d690fb168
	https://github.com/Exploder98/llama.cpp/blob/8781013ef654270cbead3e0011e33a6d690fb168/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/8781013ef654270cbead3e0011e33a6d690fb168
examples : add compiler version and target to build info (#2998)	https://github.com/Exploder98/llama.cpp/commit/e6616cf0db2b63189fc34d0076f654af9adecdf8
	https://github.com/cebtenzzre
cebtenzzre	https://github.com/Exploder98/llama.cpp/commits?author=cebtenzzre
e6616cf	https://github.com/Exploder98/llama.cpp/commit/e6616cf0db2b63189fc34d0076f654af9adecdf8
	https://github.com/Exploder98/llama.cpp/blob/e6616cf0db2b63189fc34d0076f654af9adecdf8/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/e6616cf0db2b63189fc34d0076f654af9adecdf8
check C++ code with -Wmissing-declarations (#3184)	https://github.com/Exploder98/llama.cpp/commit/3aefaab9e59335ebb07d5205dbc8633efd680e58
	https://github.com/cebtenzzre
cebtenzzre	https://github.com/Exploder98/llama.cpp/commits?author=cebtenzzre
3aefaab	https://github.com/Exploder98/llama.cpp/commit/3aefaab9e59335ebb07d5205dbc8633efd680e58
	https://github.com/Exploder98/llama.cpp/blob/3aefaab9e59335ebb07d5205dbc8633efd680e58/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/3aefaab9e59335ebb07d5205dbc8633efd680e58
fix some warnings from gcc and clang-tidy (#3038)	https://github.com/Exploder98/llama.cpp/commit/00d62adb79bf914a95fb9a2e8f42f3029e76d62c
cebtenzzre	https://github.com/Exploder98/llama.cpp/commits?author=cebtenzzre
xaedes	https://github.com/Exploder98/llama.cpp/commits?author=xaedes
00d62ad	https://github.com/Exploder98/llama.cpp/commit/00d62adb79bf914a95fb9a2e8f42f3029e76d62c
	https://github.com/Exploder98/llama.cpp/blob/00d62adb79bf914a95fb9a2e8f42f3029e76d62c/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/00d62adb79bf914a95fb9a2e8f42f3029e76d62c
Allow quantize to only copy tensors, some other improvements (#2931)	https://github.com/Exploder98/llama.cpp/commit/5d6f19f16b2173afe2d5c6aee2f5c9fc31038eba
	https://github.com/KerfuffleV2
KerfuffleV2	https://github.com/Exploder98/llama.cpp/commits?author=KerfuffleV2
5d6f19f	https://github.com/Exploder98/llama.cpp/commit/5d6f19f16b2173afe2d5c6aee2f5c9fc31038eba
	https://github.com/Exploder98/llama.cpp/blob/5d6f19f16b2173afe2d5c6aee2f5c9fc31038eba/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/5d6f19f16b2173afe2d5c6aee2f5c9fc31038eba
quantize : make output filename optional again (#2823)	https://github.com/Exploder98/llama.cpp/commit/ebcee207b6058b7f695bb5c203ad87b1066a9790
	https://github.com/cebtenzzre
cebtenzzre	https://github.com/Exploder98/llama.cpp/commits?author=cebtenzzre
ebcee20	https://github.com/Exploder98/llama.cpp/commit/ebcee207b6058b7f695bb5c203ad87b1066a9790
	https://github.com/Exploder98/llama.cpp/blob/ebcee207b6058b7f695bb5c203ad87b1066a9790/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/ebcee207b6058b7f695bb5c203ad87b1066a9790
Fix values shown in the quantize tool help (#2735)	https://github.com/Exploder98/llama.cpp/commit/8207214b6a37a46526cee9e72d4c9092b9d1872f
ikawrakow	https://github.com/Exploder98/llama.cpp/commits?author=ikawrakow
8207214	https://github.com/Exploder98/llama.cpp/commit/8207214b6a37a46526cee9e72d4c9092b9d1872f
	https://github.com/Exploder98/llama.cpp/blob/8207214b6a37a46526cee9e72d4c9092b9d1872f/examples/quantize/quantize.cpp
	https://github.com/Exploder98/llama.cpp/tree/8207214b6a37a46526cee9e72d4c9092b9d1872f
Next	https://github.com/Exploder98/llama.cpp/commits/master/examples/quantize/quantize.cpp?after=4b77ea95f56a4c49bc995f08eac62a6416875ccc+34
	https://github.com
Terms	https://docs.github.com/site-policy/github-terms/github-terms-of-service
Privacy	https://docs.github.com/site-policy/privacy-policies/github-privacy-statement
Security	https://github.com/security
Status	https://www.githubstatus.com/
Community	https://github.community/
Docs	https://docs.github.com/
Contact	https://support.github.com?tags=dotcom-footer

Viewport: width=device-width

URLs of crawlers that visited me.