Skip to content

K quant speedup#20

Merged
reeselevine merged 10 commits intomasterfrom
k_quant_speedup
Mar 3, 2026
Merged

K quant speedup#20
reeselevine merged 10 commits intomasterfrom
k_quant_speedup

Conversation

@reeselevine
Copy link
Owner

Make sure to read the contributing guidelines before submitting a PR

neha-ha and others added 8 commits February 10, 2026 19:27
* scale jit working

* preliminary working jit for getrows and mulmat, needs refining

* simplified mul_mat preprocessing switch statement

* get_rows fixes, mul_mat refinement

* formatted + last edits

* removed some extraneous prints

* fixed get_rows, fixed workgroup dispatch in mul_mat. no gibberish

* small fix

* some changes, working

* get_rows and mul_mat jit fixed and working

* Update formatting

* formatting

* Add header

---------

Co-authored-by: Neha Abbas <nehaabbas@ReeseLevines-MacBook-Pro.local>
Co-authored-by: Reese Levine <reeselevine1@gmail.com>
@reeselevine reeselevine merged commit 52058f3 into master Mar 3, 2026
52 of 70 checks passed
ArberSephirotheca pushed a commit to ArberSephirotheca/llama.cpp that referenced this pull request Mar 4, 2026
* Basic JIT compilation for mul_mat, get_rows, and scale (reeselevine#17)

* scale jit working

* preliminary working jit for getrows and mulmat, needs refining

* simplified mul_mat preprocessing switch statement

* get_rows fixes, mul_mat refinement

* formatted + last edits

* removed some extraneous prints

* fixed get_rows, fixed workgroup dispatch in mul_mat. no gibberish

* small fix

* some changes, working

* get_rows and mul_mat jit fixed and working

* Update formatting

* formatting

* Add header

---------

Co-authored-by: Neha Abbas <nehaabbas@ReeseLevines-MacBook-Pro.local>
Co-authored-by: Reese Levine <reeselevine1@gmail.com>

* Start work on all-encompassing shader library

* refactor argmax, set_rows

* Refactor all but flashattention, mat mul

* no gibberish, all k quants added, merged

* vec memory fix

* q6_k matching metal on my machine, tests passing

* Set tile size for q6_k separately

* Separate out fast shaders

---------

Co-authored-by: neha-ha <137219201+neha-ha@users.noreply.github.com>
ArberSephirotheca pushed a commit to ArberSephirotheca/llama.cpp that referenced this pull request Mar 12, 2026
…better shader parameter handling (ggml-org#20173)

* K quant speedup (reeselevine#20)

* Basic JIT compilation for mul_mat, get_rows, and scale (reeselevine#17)

* scale jit working

* preliminary working jit for getrows and mulmat, needs refining

* simplified mul_mat preprocessing switch statement

* get_rows fixes, mul_mat refinement

* formatted + last edits

* removed some extraneous prints

* fixed get_rows, fixed workgroup dispatch in mul_mat. no gibberish

* small fix

* some changes, working

* get_rows and mul_mat jit fixed and working

* Update formatting

* formatting

* Add header

---------

Co-authored-by: Neha Abbas <nehaabbas@ReeseLevines-MacBook-Pro.local>
Co-authored-by: Reese Levine <reeselevine1@gmail.com>

* Start work on all-encompassing shader library

* refactor argmax, set_rows

* Refactor all but flashattention, mat mul

* no gibberish, all k quants added, merged

* vec memory fix

* q6_k matching metal on my machine, tests passing

* Set tile size for q6_k separately

* Separate out fast shaders

---------

Co-authored-by: neha-ha <137219201+neha-ha@users.noreply.github.com>

* Move towards writeBuffer for params

* Move away from multiple buffers for set_rows errors, remove host buffer for parameter buffers, minor cleanups

* Remove extra file

* Formatting

---------

Co-authored-by: neha-ha <137219201+neha-ha@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants